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

    Neuronpedia

    INDEX
    Explanations

    detail-oriented phrases that indicate uncertainty or highlight specific issues in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cunning
    -0.18
    idar
    -0.15
    roid
    -0.15
     brun
    -0.15
    esel
    -0.15
     Starr
    -0.14
     cushion
    -0.14
    leh
    -0.14
    mis
    -0.14
    /misc
    -0.14
    POSITIVE LOGITS
    fsp
    0.17
     BÃŃ
    0.17
    utton
    0.17
    ined
    0.15
    аем
    0.15
    ullet
    0.15
    çĽijåIJ¬é¡µéĿ¢
    0.14
    /Dk
    0.14
    ioned
    0.14
    ilo
    0.14
    Act Density 0.694%

    No Known Activations