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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical objects or concepts related to providing support or structure

    oai_token-act-pair · gpt-3.5-turbo

    the word "stand" in various contexts and forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EStream
    -0.85
    nesota
    -0.79
    ertodd
    -0.73
    avascript
    -0.73
    EStreamFrame
    -0.73
    hammad
    -0.72
    actionDate
    -0.69
    olesc
    -0.69
    REDACTED
    -0.68
     Annotations
    -0.64
    POSITIVE LOGITS
    still
    1.22
    ings
    0.89
    bys
    0.88
    pipe
    0.85
    ingly
    0.85
    alone
    0.83
    mount
    0.82
    outs
    0.80
    ances
    0.74
    overs
    0.73
    Act Density 0.020%

    No Known Activations