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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "stop" in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "stop" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sov
    -0.79
    VERTISEMENT
    -0.75
    ighth
    -0.75
    ammy
    -0.71
    umbered
    -0.70
    olesc
    -0.70
    alty
    -0.70
    opter
    -0.69
    aths
    -0.68
    inged
    -0.68
    POSITIVE LOGITS
    watch
    0.91
    gap
    0.91
    watching
    0.84
    reon
    0.80
     bothering
    0.80
     stopping
    0.77
     blinking
    0.76
     wasting
    0.73
     smoking
    0.72
     Stop
    0.70
    Act Density 0.024%

    No Known Activations