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

    Neuronpedia

    INDEX
    Explanations

    names or terms with the prefix "Ab-" followed by varying suffixes

    oai_token-act-pair · gpt-3.5-turbo

    words related to Arabic names and terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    voy
    -0.77
    perature
    -0.74
    £ı
    -0.69
    arnaev
    -0.68
    pieces
    -0.64
    uania
    -0.64
    SOURCE
    -0.64
     gears
    -0.63
    uters
    -0.63
    finding
    -0.63
    POSITIVE LOGITS
    ÃĽ
    0.76
    ILA
    0.70
    dash
    0.68
    uary
    0.66
     Laboratories
    0.66
     Genocide
    0.64
    Ø©
    0.63
    Attempt
    0.62
    SourceFile
    0.61
     Mine
    0.61
    Act Density 0.134%

    No Known Activations