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

    Neuronpedia

    INDEX
    Explanations

    features or aspects that distinguish one thing from others

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases that highlight distinctiveness among various subjects or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouple
    -0.86
    ossession
    -0.85
    riber
    -0.82
    earance
    -0.76
    Putin
    -0.74
    eness
    -0.72
    urden
    -0.71
    bec
    -0.69
    matter
    -0.69
    ossibility
    -0.68
    POSITIVE LOGITS
     types
    1.12
     alternatives
    1.10
     forms
    1.09
     kinds
    1.06
     competitors
    1.06
     brands
    1.06
     contemporary
    1.04
     contenders
    1.04
     implementations
    1.03
     modern
    1.03
    Act Density 0.160%

    No Known Activations