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

    Neuronpedia

    INDEX
    Explanations

    references to progress or advancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    progress and its context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     peak
    -0.53
     shadow
    -0.46
    __":
    -0.42
    enterOuterAlt
    -0.41
    peak
    -0.41
     coinc
    -0.41
    UrlResolution
    -0.41
     Peak
    -0.40
     shadows
    -0.40
     quir
    -0.39
    POSITIVE LOGITS
     progress
    1.19
    Progress
    1.09
    progress
    1.07
     Progress
    1.05
     PROGRESS
    0.93
    PROGRESS
    0.92
     Fortsch
    0.90
     progresses
    0.86
     progresso
    0.84
     progreso
    0.83
    Act Density 0.066%

    No Known Activations