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

    Neuronpedia

    INDEX
    Explanations

    keywords related to a specific point in time or a stage in a process

    oai_token-act-pair · gpt-3.5-turbo

    references to specific points in time or momentary situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avorite
    -0.79
     flyers
    -0.70
     warranties
    -0.69
    urat
    -0.66
     Sins
    -0.66
    itton
    -0.65
    tty
    -0.64
    onut
    -0.64
    harm
    -0.63
     masc
    -0.63
    POSITIVE LOGITS
     onwards
    0.95
     onward
    0.81
    point
    0.78
    cture
    0.76
    Stage
    0.75
    anu
    0.74
    points
    0.72
     point
    0.69
     iteration
    0.69
     stage
    0.69
    Act Density 0.030%

    No Known Activations