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

    Neuronpedia

    INDEX
    Explanations

    words related to suggestions or recommendations

    oai_token-act-pair · gpt-3.5-turbo

    phrases questioning or challenging the status quo

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    photo
    -0.74
    ELD
    -0.72
    digit
    -0.70
    utch
    -0.68
    iple
    -0.66
    Reviewed
    -0.65
    chairs
    -0.64
    vor
    -0.63
    iHUD
    -0.61
    ItemTracker
    -0.61
    POSITIVE LOGITS
     indulge
    0.87
    ?]
    0.86
     emulate
    0.81
    itia
    0.79
     unleash
    0.77
     succumb
    0.74
     abolish
    0.74
     invoke
    0.74
     intervene
    0.74
     recreate
    0.73
    Act Density 0.028%

    No Known Activations