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

    Neuronpedia

    INDEX
    Explanations

    questions asking for opinions or thoughts on various topics or articles

    oai_token-act-pair · gpt-3.5-turbo

    questions and phrases related to opinions or thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vity
    -0.82
    ruit
    -0.78
    ante
    -0.77
    ulo
    -0.70
    arms
    -0.68
    abo
    -0.68
    dig
    -0.67
    rote
    -0.67
    ynthesis
    -0.66
    ring
    -0.66
    POSITIVE LOGITS
     whether
    0.75
    76561
    0.72
     behalf
    0.71
     homosexuality
    0.71
    Rating
    0.70
     unres
    0.69
     respecting
    0.69
    awed
    0.67
     aloud
    0.67
     regard
    0.66
    Act Density 0.124%

    No Known Activations