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

    Neuronpedia

    INDEX
    Explanations

    phrases related to risk and relationships in creative or social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azu
    -0.15
    le
    -0.14
    rief
    -0.14
    endez
    -0.14
    illes
    -0.14
    este
    -0.14
    p
    -0.14
    enz
    -0.14
    this
    -0.13
    unal
    -0.13
    POSITIVE LOGITS
    è¶Ĭ
    0.36
     cÃłng
    0.30
     fewer
    0.16
     è¶
    0.15
     ÏĦÏĮÏĥο
    0.15
    ignKey
    0.15
     greater
    0.15
    .cc
    0.14
    *)((
    0.14
    agos
    0.14
    Act Density 0.026%

    No Known Activations