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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and thanks

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude or thanks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    place
    -0.80
    Ranked
    -0.77
    ember
    -0.77
    conserv
    -0.76
    opers
    -0.71
    dq
    -0.69
    objects
    -0.67
    ther
    -0.66
    wide
    -0.65
    hazard
    -0.64
    POSITIVE LOGITS
    giving
    0.97
    fulness
    0.87
     God
    0.82
     donors
    0.81
    ESCO
    0.80
     contributors
    0.80
     colleagues
    0.77
     constituents
    0.76
     thank
    0.73
    FUL
    0.73
    Act Density 0.022%

    No Known Activations