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

    Neuronpedia

    INDEX
    Explanations

    websites or online sources

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "com."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Balt
    -0.68
     burgl
    -0.67
     Wilde
    -0.65
     Lump
    -0.63
     cub
    -0.61
     lifes
    -0.60
    Berry
    -0.58
     restraining
    -0.58
     Tarant
    -0.58
     Gor
    -0.58
    POSITIVE LOGITS
    pleted
    1.14
    fortable
    1.03
    pletion
    1.00
    puters
    1.00
    lisher
    0.99
    ptroller
    0.97
    lishing
    0.96
    com
    0.91
    ittal
    0.91
    ittee
    0.89
    Act Density 0.032%

    No Known Activations