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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a future action or outcome

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "end up" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ongyang
    -0.67
    gee
    -0.66
    heed
    -0.66
    mouth
    -0.65
     assurance
    -0.65
    cut
    -0.63
    bay
    -0.61
    ature
    -0.60
     description
    -0.60
    "]=>
    -0.60
    POSITIVE LOGITS
    ãĥĩãĤ£
    0.68
    aterasu
    0.68
    icably
    0.67
    ymes
    0.66
     redes
    0.66
    skirts
    0.64
     getting
    0.64
    adesh
    0.64
    Ñĭ
    0.64
    votes
    0.63
    Act Density 0.028%

    No Known Activations