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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "pulled"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pulled."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibel
    -0.74
    nam
    -0.72
    lain
    -0.71
    vous
    -0.70
    esan
    -0.70
     Scope
    -0.69
    unic
    -0.68
    antics
    -0.68
    heid
    -0.68
    icol
    -0.68
    POSITIVE LOGITS
    pull
    1.08
     pull
    0.96
    Pull
    0.94
     pulled
    0.85
     aggro
    0.85
     pulls
    0.83
     pulling
    0.83
     Pull
    0.80
    lift
    0.75
     weeds
    0.69
    Act Density 0.014%

    No Known Activations