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

    Neuronpedia

    INDEX
    Explanations

    phrases where something or someone is being evaluated or judged as having a particular status or characteristic

    oai_token-act-pair · gpt-3.5-turbo

    statements that involve the act of being regarded or labeled in a certain way

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inas
    -0.68
    hire
    -0.67
    brow
    -0.64
    sheets
    -0.63
    load
    -0.62
    loads
    -0.62
    letter
    -0.61
    arling
    -0.60
     Herrera
    -0.59
    Ring
    -0.59
    POSITIVE LOGITS
    phas
    0.95
     favorably
    0.91
     Tradable
    0.84
     infall
    0.74
     expend
    0.73
     canon
    0.73
    soDeliveryDate
    0.71
     considered
    0.71
     "$:/
    0.71
     cel
    0.71
    Act Density 0.030%

    No Known Activations