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

    Neuronpedia

    INDEX
    Explanations

    markers indicating code structure or data definition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Бахар
    -0.60
     soli
    -0.58
     analysing
    -0.55
     Roskov
    -0.55
    asanjo
    -0.53
     envelopes
    -0.50
     CascadeType
    -0.50
    稲田
    -0.49
    Filmographie
    -0.49
     Kowalski
    -0.49
    POSITIVE LOGITS
    else
    0.91
    Rhestr
    0.88
     else
    0.88
     الدولى
    0.74
     Otherwise
    0.67
    Otherwise
    0.66
     étranger
    0.64
     prisonniers
    0.63
    otherwise
    0.62
     otherwise
    0.62
    Act Density 0.043%

    No Known Activations