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

    Neuronpedia

    INDEX
    Explanations

    the use of the word "whatever" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anford
    -0.15
    ücken
    -0.15
    )(((
    -0.15
    rrha
    -0.15
    zung
    -0.14
    uner
    -0.14
    lops
    -0.14
    ure
    -0.14
    ByPrimaryKey
    -0.14
    @brief
    -0.13
    POSITIVE LOGITS
     punct
    0.16
    ÑĢог
    0.15
     aver
    0.14
    :^
    0.14
    asc
    0.14
     Chuck
    0.13
    -clock
    0.13
    596
    0.13
    xico
    0.13
     Fool
    0.13
    Act Density 0.010%

    No Known Activations