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

    Neuronpedia

    INDEX
    Explanations

    phrases where someone is explaining something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Donation
    -0.70
     botched
    -0.62
     Accessed
    -0.62
     showers
    -0.60
     wastes
    -0.58
     Opportun
    -0.57
     allotted
    -0.57
     Volunte
    -0.56
    .–
    -0.56
     improvised
    -0.56
    POSITIVE LOGITS
    ilet
    1.02
    othy
    0.95
    ggles
    0.92
    wered
    0.90
    pless
    0.86
     me
    0.83
     satisfy
    0.82
     us
    0.81
     appease
    0.81
     justify
    0.79
    Act Density 0.199%

    No Known Activations