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

    Neuronpedia

    INDEX
    Explanations

    statements that express certainty or obviousness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UserScript
    -0.42
     eddy
    -0.41
     rumor
    -0.40
    Rüyada
    -0.37
    sizeCache
    -0.37
     Rptr
    -0.36
    ="@+
    -0.35
    WriteAttribute
    -0.35
     يتيمه
    -0.35
     rumors
    -0.35
    POSITIVE LOGITS
     obviously
    1.30
    obviously
    1.25
    Obviously
    1.24
     Obviously
    1.22
     obvious
    1.10
     clearly
    1.09
    Clearly
    1.09
    obvious
    1.06
     Clearly
    1.06
    clearly
    1.02
    Act Density 0.238%

    No Known Activations