Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions of personal experience and sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words after "said" and attribution

    np_acts-logits-general · gemini-2.5-flash-lite

    Lines of direct speech or quoted dialogue (speaker attributions and tokens inside quotations).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.41
     ABS
    -0.38
    Interop
    -0.37
     Bureau
    -0.36
    borders
    -0.35
     besto
    -0.35
    DotNetBar
    -0.35
     InputDecoration
    -0.35
     Hyp
    -0.34
     New
    -0.34
    POSITIVE LOGITS
    GEBURTS
    0.61
     invokingState
    0.60
     AssemblyCulture
    0.53
     насељу
    0.52
    pecabe
    0.51
    rsiniz
    0.50
     desmotivaciones
    0.50
     increí
    0.50
    OCCURRED
    0.48
    Życiorys
    0.47
    Act Density 0.290%

    No Known Activations