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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences indicating opinions or declarations, often starting with "said it was."

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases indicating assertion or confirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     confines
    -0.74
    enment
    -0.71
    alus
    -0.67
    ossom
    -0.67
    aign
    -0.65
    acly
    -0.65
     stroll
    -0.61
    atives
    -0.61
    vertisement
    -0.60
    fts
    -0.60
    POSITIVE LOGITS
     owed
    0.75
    ©¶æ
    0.71
     not
    0.70
    absolutely
    0.70
    uten
    0.67
    Ĥİ
    0.67
     "#
    0.66
    NOT
    0.66
     intentionally
    0.65
    not
    0.65
    Act Density 0.370%

    No Known Activations