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

    Neuronpedia

    INDEX
    Explanations

    words related to awards or achievements

    oai_token-act-pair · gpt-3.5-turbo

    references to award-winning achievements or accolades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omach
    -0.74
    thia
    -0.72
    enhagen
    -0.69
    seless
    -0.68
    matter
    -0.65
    umo
    -0.65
    idation
    -0.64
    agen
    -0.63
    matic
    -0.63
    ogy
    -0.62
    POSITIVE LOGITS
     actress
    0.89
     novelist
    0.85
     Pulitzer
    0.83
     author
    0.82
     filmmaker
    0.82
     journalist
    0.81
     heroine
    0.80
     bestselling
    0.80
     documentary
    0.78
     artist
    0.78
    Act Density 0.070%

    No Known Activations