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

    Neuronpedia

    INDEX
    Explanations

    conditional statements indicating possibilities or conditions

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases that imply specific scenarios or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quit
    -0.69
    gur
    -0.67
    hibited
    -0.64
    activate
    -0.63
    continue
    -0.62
    hole
    -0.61
    ude
    -0.60
    helial
    -0.60
    lez
    -0.60
    aunder
    -0.59
    POSITIVE LOGITS
     you
    0.91
     accompanied
    0.87
     coupled
    0.85
     there
    0.83
     compared
    0.82
     paired
    0.78
     contrasted
    0.77
     they
    0.75
     someone
    0.74
     somebody
    0.72
    Act Density 0.144%

    No Known Activations