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

    Neuronpedia

    INDEX
    Explanations

    It looks for statements indicating knowledge or information

    oai_token-act-pair · gpt-3.5-turbo

    statements of knowledge or factual assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pex
    -0.87
    oshenko
    -0.75
    cit
    -0.73
    cific
    -0.67
    cohol
    -0.65
    otti
    -0.65
    cus
    -0.65
    ksh
    -0.64
    onies
    -0.64
    rentice
    -0.64
    POSITIVE LOGITS
     ourselves
    0.85
     how
    0.73
    ledge
    0.71
    ledged
    0.71
     plenty
    0.71
    ariat
    0.68
     hinges
    0.66
    lege
    0.62
     enough
    0.62
     nothing
    0.62
    Act Density 0.090%

    No Known Activations