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

    Neuronpedia

    INDEX
    Explanations

    references to cyber-related topics and vocabulary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Caption
    -1.82
    ailing
    -1.68
     descent
    -1.64
     previous
    -1.48
     other
    -1.47
     lack
    -1.44
     mind
    -1.44
     longest
    -1.42
    ails
    -1.41
    izations
    -1.40
    POSITIVE LOGITS
    °
    2.20
    ¤
    1.96
    ł
    1.96
    ģ
    1.95
    Ł
    1.94
    tochrome
    1.94
    Ķ
    1.93
    ²
    1.93
    Ĵ
    1.85
    Ļ
    1.85
    Act Density 0.157%

    No Known Activations