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

    Neuronpedia

    INDEX
    Explanations

    uppercase words

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "VER" and its variations, indicating a focus on verbal forms or constructs in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    waukee
    -0.77
    apple
    -0.71
    antry
    -0.64
     Rite
    -0.64
    appings
    -0.63
    ulton
    -0.63
    Tags
    -0.63
    ophys
    -0.63
    ensing
    -0.62
    ById
    -0.62
    POSITIVE LOGITS
    VER
    1.46
    theless
    0.97
    ver
    0.92
    VERS
    0.89
    IFIED
    0.89
    dict
    0.88
    POSE
    0.77
    VO
    0.76
    ERN
    0.75
    IFIC
    0.75
    Act Density 0.005%

    No Known Activations