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

    Neuronpedia

    INDEX
    Explanations

    mentions of award-winning 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
    agen
    -0.81
    ocene
    -0.77
    alle
    -0.76
    utterstock
    -0.76
    omach
    -0.76
    abus
    -0.74
    elo
    -0.72
    idium
    -0.71
    vere
    -0.70
    agara
    -0.70
    POSITIVE LOGITS
     Pulitzer
    0.75
     actress
    0.73
     novelist
    0.70
     performer
    0.67
     journalist
    0.67
     darling
    0.67
     filmmaker
    0.67
     violin
    0.65
     bestselling
    0.65
    theless
    0.65
    Act Density 0.064%

    No Known Activations