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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to people or places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    guang
    -0.70
    ioare
    -0.68
    guo
    -0.66
    ingh
    -0.65
    -------
    -0.64
    gong
    -0.63
    tro
    -0.63
    sound
    -0.62
    ceq
    -0.62
    RESERVED
    -0.62
    POSITIVE LOGITS
    ning
    0.73
    nnnn
    0.70
    na
    0.69
    ek
    0.66
    er
    0.65
    alysis
    0.63
    nah
    0.63
    ran
    0.59
    en
    0.59
    NNNN
    0.59
    Act Density 0.352%

    No Known Activations