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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to reversal or changing direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eller
    -0.16
    ÑĢиз
    -0.16
    ideographic
    -0.16
    erv
    -0.15
    nap
    -0.15
    ride
    -0.15
    lb
    -0.15
    GF
    -0.15
    lain
    -0.15
    locker
    -0.14
    POSITIVE LOGITS
    /back
    0.20
    lrt
    0.17
     Rubin
    0.16
    енÑĮ
    0.15
    atham
    0.15
    =back
    0.15
    /trans
    0.15
    cek
    0.14
    -inverse
    0.14
    mdb
    0.14
    Act Density 0.041%

    No Known Activations