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

    Neuronpedia

    INDEX
    Explanations

    mentions of organizations or entities

    oai_token-act-pair · gpt-3.5-turbo

    the word "its" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.71
     contrace
    -0.71
    ľ
    -0.69
    ·
    -0.65
    cknow
    -0.65
    ¥µ
    -0.64
     destro
    -0.64
    ´
    -0.62
    ATHER
    -0.62
     [|
    -0.62
    POSITIVE LOGITS
    gerald
    1.03
    itute
    1.00
    ters
    0.98
    matter
    0.96
    creen
    0.91
    chens
    0.91
    ariat
    0.88
    ettings
    0.87
    itution
    0.84
    uary
    0.82
    Act Density 0.032%

    No Known Activations