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

    Neuronpedia

    INDEX
    Explanations

    words containing the specific letters "Ver" followed by a single digit

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Ver" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    »Ĵ
    -0.90
    iewicz
    -0.70
    cffffcc
    -0.69
    ENDED
    -0.68
    akings
    -0.66
    ħĭ
    -0.66
    utics
    -0.66
     Telescope
    -0.65
     haze
    -0.65
    ovie
    -0.65
    POSITIVE LOGITS
    Ver
    1.11
     Ver
    1.11
    dict
    0.92
    bal
    0.91
    ver
    0.89
    ified
    0.86
    bum
    0.85
     ver
    0.81
    gence
    0.81
    vers
    0.79
    Act Density 0.005%

    No Known Activations