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

    Neuronpedia

    INDEX
    Explanations

    elements related to constructive communication and relationships

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

    concepts and contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SharedDtor
    -0.46
     but
    -0.43
     also
    -0.40
    ViewInit
    -0.38
    AnchorStyles
    -0.37
    UnknownFieldSet
    -0.37
    ioutil
    -0.36
    idom
    -0.36
     recommended
    -0.36
    timeScale
    -0.35
    POSITIVE LOGITS
     ſta
    0.72
     myſelf
    0.66
     ſal
    0.65
     ſte
    0.65
     ſon
    0.63
     faſt
    0.62
     ſtre
    0.61
     ſol
    0.61
     Houſe
    0.60
     pleaſure
    0.60
    Act Density 0.041%

    No Known Activations