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

    Neuronpedia

    INDEX
    Explanations

    words related to valuable items

    oai_token-act-pair · gpt-3.5-turbo

    words related to value and valuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    merce
    -0.84
    gypt
    -0.60
     wom
    -0.58
     fronts
    -0.58
    tale
    -0.58
     Seventh
    -0.57
    selves
    -0.56
     Hera
    -0.56
    enegger
    -0.54
     rotated
    -0.53
    POSITIVE LOGITS
    ãĤ£
    0.77
    oso
    0.76
    rations
    0.74
    anamo
    0.71
    athan
    0.69
    ão
    0.68
    idated
    0.67
    iant
    0.67
    otten
    0.66
    emale
    0.65
    Act Density 0.077%

    No Known Activations