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

    Neuronpedia

    INDEX
    Explanations

    phrases related to continuous motion or change

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "stra" and related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.86
     DOI
    -0.72
    66666666
    -0.68
     Killer
    -0.67
     AQ
    -0.65
     Loving
    -0.64
     CTR
    -0.63
     PDT
    -0.63
    Interstitial
    -0.61
     Laden
    -0.60
    POSITIVE LOGITS
    stra
    1.56
    ©¶æ
    0.95
     contrace
    0.85
    ÃŁ
    0.81
    uckland
    0.78
    ratulations
    0.78
    pling
    0.78
    pped
    0.77
    cipled
    0.77
     traged
    0.77
    Act Density 0.006%

    No Known Activations