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

    Neuronpedia

    INDEX
    Explanations

    mentions of meetings or encounters

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Meet" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wcs
    -0.88
    secut
    -0.79
    vernment
    -0.77
    cffffcc
    -0.74
     destro
    -0.71
    ¥ŀ
    -0.70
    peria
    -0.69
    secution
    -0.68
    cul
    -0.67
    ierce
    -0.66
    POSITIVE LOGITS
    ings
    1.17
    ãĤ¤ãĥĪ
    0.95
     Meet
    0.89
    athon
    0.87
    INGS
    0.87
    Meet
    0.86
    aunt
    0.83
    ingly
    0.83
    amorph
    0.82
    icles
    0.81
    Act Density 0.016%

    No Known Activations