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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and definitions related to code structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (!__
    -0.68
     مرئيه
    -0.65
    AndEndTag
    -0.65
    protoimpl
    -0.57
     estatal
    -0.55
     rêver
    -0.55
    NameInMap
    -0.55
    labelledby
    -0.55
     unknownFields
    -0.54
     pescoço
    -0.53
    POSITIVE LOGITS
    _',
    0.72
    _'+
    0.66
    _))
    0.64
    annica
    0.64
    themselves
    0.63
    _;
    0.62
    _<
    0.60
    _=
    0.60
    _()
    0.60
     themselves
    0.59
    Act Density 0.196%

    No Known Activations