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

    Neuronpedia

    INDEX
    Explanations

    phrases related to completing, finishing, or summarizing something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to concluding or finishing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogi
    -0.73
    acus
    -0.72
     Haas
    -0.68
    appropri
    -0.62
     alter
    -0.61
    bee
    -0.60
     caf
    -0.59
    acist
    -0.58
     spoof
    -0.57
    chens
    -0.56
    POSITIVE LOGITS
    Ń·
    0.91
    sett
    0.78
     Winds
    0.72
    ¥µ
    0.69
    EVA
    0.67
    lished
    0.66
    mortem
    0.65
     landfall
    0.65
    byss
    0.65
    doors
    0.65
    Act Density 0.054%

    No Known Activations