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

    Neuronpedia

    INDEX
    Explanations

    instances of a particular point or moment in time

    oai_token-act-pair · gpt-3.5-turbo

    references to critical moments or turning points in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yet
    -0.68
    ords
    -0.66
    velop
    -0.66
    atts
    -0.65
    liction
    -0.63
    little
    -0.63
    STEM
    -0.62
    goo
    -0.62
    anders
    -0.62
    riger
    -0.61
    POSITIVE LOGITS
     during
    0.90
    upon
    0.80
     throughout
    0.76
     thereafter
    0.75
     onwards
    0.73
     midway
    0.69
     along
    0.68
     culminating
    0.68
     apiece
    0.65
     onward
    0.65
    Act Density 0.044%

    No Known Activations