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

    Neuronpedia

    INDEX
    Explanations

    phrases suggesting a desirable or ideal scenario

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MainAxisSize
    -0.86
    moiselle
    -0.67
    BuildContext
    -0.63
    HtmlAttribute
    -0.57
    verschluss
    -0.57
    dafx
    -0.55
    qtype
    -0.54
     pama
    -0.53
    зион
    -0.51
    ElementException
    -0.50
    POSITIVE LOGITS
     nice
    0.96
     rem
    0.77
     ideal
    0.76
     great
    0.74
    nice
    0.70
     Would
    0.68
    ideal
    0.67
     would
    0.67
    Would
    0.62
     amiss
    0.62
    Act Density 0.149%

    No Known Activations