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

    Neuronpedia

    INDEX
    Explanations

    names of famous individuals, particularly in relation to controversies or significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éħį
    -0.16
    quez
    -0.16
    ICS
    -0.15
    ullen
    -0.14
    LOGY
    -0.14
    奶
    -0.14
    ener
    -0.13
    ensing
    -0.13
    _FE
    -0.13
     Fold
    -0.13
    POSITIVE LOGITS
    licer
    0.16
    ãĥ©ãĥ³ãĥī
    0.16
    èĪį
    0.15
    à¸ģ
    0.15
    #w
    0.15
    illin
    0.15
    Isl
    0.15
     Mixer
    0.15
    rej
    0.14
    peg
    0.14
    Act Density 0.003%

    No Known Activations