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

    Neuronpedia

    INDEX
    Explanations

    elements related to endorsements or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -S
    -0.35
    -s
    -0.35
    _S
    -0.34
    .S
    -0.31
    _s
    -0.31
     S
    -0.29
    ãĤµ
    -0.28
    ãĤ¹
    -0.27
    ÂłS
    -0.27
    स
    -0.26
    POSITIVE LOGITS
     æ¼
    0.15
    ãĥķãĤ©
    0.15
    PF
    0.15
    kus
    0.14
    ãĥı
    0.14
    IMER
    0.14
    tÃŃ
    0.14
    iku
    0.14
    _READY
    0.14
    !=(
    0.13
    Act Density 0.136%

    No Known Activations