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

    Neuronpedia

    INDEX
    Explanations

    financial and numerical terms

    oai_token-act-pair · gpt-3.5-turbo

    topics related to academic and financial metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izons
    -0.79
    aughs
    -0.76
    vantage
    -0.71
    apego
    -0.68
    ournal
    -0.68
    acebook
    -0.67
    uilt
    -0.66
    enegger
    -0.65
    isites
    -0.63
    rists
    -0.63
    POSITIVE LOGITS
     guise
    1.00
     manner
    0.88
     mode
    0.85
     form
    0.83
     circles
    0.82
     fashion
    0.81
     contexts
    0.77
     increments
    0.77
     folklore
    0.73
     estimation
    0.72
    Act Density 0.407%

    No Known Activations