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

    Neuronpedia

    INDEX
    Explanations

    instances of preparation and initiation of actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    >.
    -0.72
    MON
    -0.68
     altogether
    -0.65
    unless
    -0.65
    tec
    -0.63
    $.
    -0.62
    illegal
    -0.62
    found
    -0.62
    collar
    -0.60
    CN
    -0.59
    POSITIVE LOGITS
     dwindling
    0.82
     unfolds
    0.72
     unfold
    0.72
     intens
    0.72
     progresses
    0.70
     dusk
    0.70
     fading
    0.69
     dawn
    0.68
     fades
    0.68
     twilight
    0.68
    Act Density 0.113%

    No Known Activations