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

    Neuronpedia

    INDEX
    Explanations

    semicolons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases indicating an action or decision about to be taken

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    orts
    -0.78
    Bas
    -0.68
    WAY
    -0.66
    inki
    -0.65
    Accessory
    -0.65
    IDENT
    -0.65
    hedral
    -0.64
    aved
    -0.64
    ema
    -0.64
    se
    -0.63
    POSITIVE LOGITS
     namely
    1.08
    -)
    1.08
     moreover
    1.01
     furthermore
    0.99
     hence
    0.99
     alas
    0.95
     alternatively
    0.94
     nevertheless
    0.89
     however
    0.89
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.89
    Act Density 0.042%

    No Known Activations