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

    Neuronpedia

    INDEX
    Explanations

    words related to acknowledgement or recognition

    oai_token-act-pair · gpt-3.5-turbo

    terms related to recognition or attribution of credit

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VER
    -0.69
     mosquit
    -0.68
    icz
    -0.66
    FO
    -0.63
    improve
    -0.63
    axe
    -0.63
    oret
    -0.62
    xy
    -0.61
    edIn
    -0.61
    ften
    -0.60
    POSITIVE LOGITS
    olor
    0.90
     credits
    0.84
    heet
    0.80
    VERTISEMENT
    0.78
    enza
    0.74
     card
    0.74
    fulness
    0.71
    redited
    0.71
    urden
    0.71
     Credits
    0.70
    Act Density 0.023%

    No Known Activations