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

    Neuronpedia

    INDEX
    Explanations

    instances where the term "threshold" is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    references to specific thresholds and their implications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulf
    -0.86
    ateur
    -0.70
    iga
    -0.67
    fortune
    -0.65
    wagen
    -0.63
    thora
    -0.62
    ocation
    -0.62
    obbies
    -0.62
    asca
    -0.61
    arus
    -0.61
    POSITIVE LOGITS
     thresholds
    0.91
     threshold
    0.89
    posts
    0.85
     clearance
    0.84
    post
    0.78
    ansas
    0.76
    witz
    0.74
     cutoff
    0.71
    pole
    0.69
    =$
    0.69
    Act Density 0.033%

    No Known Activations