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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or tasks

    oai_token-act-pair · gpt-3.5-turbo

    actions related to reporting or documenting activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Seym
    -0.60
    licted
    -0.60
     Vaugh
    -0.57
    attering
    -0.55
    esides
    -0.52
    Luckily
    -0.49
     shockingly
    -0.49
     Berm
    -0.48
     Rowe
    -0.48
    riks
    -0.48
    POSITIVE LOGITS
     RELEASE
    0.88
     ASAP
    0.66
    ();
    0.57
     Quote
    0.57
    .--
    0.57
     Reply
    0.57
     ();
    0.54
     Unicode
    0.54
    %:
    0.54
    externalActionCode
    0.54
    Act Density 0.315%

    No Known Activations