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

    Neuronpedia

    INDEX
    Explanations

    instances of confusion or surprise in situational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     contract
    -0.17
     Contract
    -0.16
    ,
    -0.15
    sdale
    -0.14
     Caught
    -0.14
     Rising
    -0.14
    Contract
    -0.14
     bring
    -0.14
     unst
    -0.14
    åĸĦ
    -0.13
    POSITIVE LOGITS
    isay
    0.15
    emiz
    0.15
    جاÙĨ
    0.15
    eydi
    0.14
    .readyState
    0.14
    оÑĢаÑı
    0.14
    vfs
    0.14
    idine
    0.14
    ANCEL
    0.14
    :CGRect
    0.14
    Act Density 0.309%

    No Known Activations