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

    Neuronpedia

    INDEX
    Explanations

    the starting token of a document or a new section within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    μία
    -0.52
     hero
    -0.51
    kita
    -0.51
    voc
    -0.51
     Flas
    -0.49
     Hayes
    -0.49
     gainera
    -0.48
    UIAlert
    -0.48
    ícil
    -0.48
    featureID
    -0.48
    POSITIVE LOGITS
    <bos>
    0.71
    UnknownFieldSet
    0.69
    DataAnnotations
    0.67
    >{@
    0.66
    󠁿
    0.62
    )_/¯
    0.62
    ędziesz
    0.59
    VersionUID
    0.59
    expandindo
    0.59
    ंदीखरीदारी
    0.58
    Act Density 0.060%

    No Known Activations