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

    Neuronpedia

    INDEX
    Explanations

    the prefix "com-"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "com."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kubrick
    -0.69
     Chop
    -0.67
    512
    -0.63
    oux
    -0.63
    538
    -0.61
     Icelandic
    -0.56
     Sloven
    -0.56
     Slav
    -0.55
     vetting
    -0.55
     herpes
    -0.55
    POSITIVE LOGITS
    ptroller
    1.11
    forts
    1.03
     com
    0.96
    clud
    0.86
    mented
    0.80
    etary
    0.77
    otion
    0.76
    legate
    0.76
    nder
    0.76
    rade
    0.75
    Act Density 0.004%

    No Known Activations