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

    Neuronpedia

    INDEX
    Explanations

    statements where a case is being made or argued for

    oai_token-act-pair · gpt-3.5-turbo

    arguments or claims being made

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Seym
    -0.80
    ummer
    -0.72
    attery
    -0.69
    onder
    -0.69
    elta
    -0.65
    semb
    -0.64
    kered
    -0.62
    umber
    -0.62
    ombs
    -0.61
     Pixie
    -0.61
    POSITIVE LOGITS
     against
    0.82
    cases
    0.80
    Against
    0.79
     convinc
    0.78
    case
    0.73
     why
    0.72
     persuasive
    0.72
     compelling
    0.71
     convincing
    0.70
    .","
    0.70
    Act Density 0.032%

    No Known Activations