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

    Neuronpedia

    INDEX
    Explanations

    moments or starting points in time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a starting point or initial moment in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    regon
    -0.84
    ican
    -0.76
    rosso
    -0.75
    >>\
    -0.74
    Percent
    -0.73
    Mex
    -0.72
    rored
    -0.72
    RAL
    -0.68
    Els
    -0.65
    lez
    -0.64
    POSITIVE LOGITS
     standpoint
    1.34
     onwards
    1.23
     perspective
    1.20
     onward
    1.08
     perspectives
    0.99
     viewpoint
    0.98
     vantage
    0.96
     inception
    0.93
     outset
    0.87
     angle
    0.73
    Act Density 0.125%

    No Known Activations