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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and interactions

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

    phrases indicating personal experiences or interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Савезне
    -0.95
     مرئيه
    -0.94
    PhysRevLett
    -0.88
    WriteTagHelper
    -0.84
    AndEndTag
    -0.83
    IVEREF
    -0.83
     Taktlose
    -0.80
    TypedDataSet
    -0.80
     Приступљено
    -0.78
    UserScript
    -0.78
    POSITIVE LOGITS
    do
    0.41
    me
    0.38
    he
    0.37
    sp
    0.36
    defineProperty
    0.36
     personally
    0.36
    (
    0.35
    No
    0.35
    mer
    0.35
    ar
    0.35
    Act Density 0.566%

    No Known Activations