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

    Neuronpedia

    INDEX
    Explanations

    the word "assert" as well as related concepts and actions

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "assert" and related expressions of assertion or confidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Carbuncle
    -0.76
    ppo
    -0.70
     Bake
    -0.67
    bies
    -0.66
    shows
    -0.66
     Watching
    -0.64
    nton
    -0.63
    fell
    -0.63
    oho
    -0.63
    MET
    -0.62
    POSITIVE LOGITS
    ively
    1.00
    iveness
    0.94
    uable
    0.90
    uably
    0.89
    antly
    0.88
    ive
    0.87
    ements
    0.85
    ieth
    0.85
    olated
    0.84
    ially
    0.82
    Act Density 0.030%

    No Known Activations