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

    Neuronpedia

    INDEX
    Explanations

    words containing the sequence "com"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "com"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wolves
    -0.65
     encl
    -0.64
     regard
    -0.60
     Alaska
    -0.60
     recall
    -0.59
     Icelandic
    -0.59
     Wisconsin
    -0.59
     Shining
    -0.58
     rave
    -0.57
     withholding
    -0.57
    POSITIVE LOGITS
    puters
    1.63
    puting
    1.56
    pleted
    1.56
    pletion
    1.45
    fortable
    1.45
    pleting
    1.44
    parable
    1.43
    plement
    1.43
    edy
    1.37
    puted
    1.35
    Act Density 0.026%

    No Known Activations