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

    Neuronpedia

    INDEX
    Explanations

    verbs related to unintentional actions or discoveries

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "stumble" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atu
    -0.77
    orthern
    -0.77
     subp
    -0.74
    cise
    -0.70
    entric
    -0.69
    autical
    -0.69
    cell
    -0.68
    icides
    -0.67
    ntil
    -0.67
    uctor
    -0.67
    POSITIVE LOGITS
     stumble
    1.08
     stumbling
    0.90
     stumbled
    0.90
    weed
    0.88
     Corpse
    0.80
     stomp
    0.77
    bling
    0.74
     Mulcair
    0.74
    bled
    0.73
     fumble
    0.70
    Act Density 0.011%

    No Known Activations