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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases with actions followed by a period

    oai_token-act-pair · gpt-3.5-turbo

    sentence endings or punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awei
    -0.75
    agar
    -0.68
    vati
    -0.65
    gemony
    -0.64
    ellectual
    -0.64
    esty
    -0.64
     diseng
    -0.64
    ocial
    -0.64
     unbeaten
    -0.62
    errilla
    -0.61
    POSITIVE LOGITS
    ENTION
    0.73
    LIST
    0.69
     LIFE
    0.68
    Specifically
    0.67
    WARNING
    0.67
    Consider
    0.67
    FR
    0.66
    RELATED
    0.66
    Owner
    0.66
    TABLE
    0.66
    Act Density 0.321%

    No Known Activations