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

    Neuronpedia

    INDEX
    Explanations

    references to slopes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zone
    -0.17
    uar
    -0.15
     McGr
    -0.15
     tol
    -0.14
    flip
    -0.14
    æ£
    -0.14
    .converter
    -0.14
    agma
    -0.14
    uyen
    -0.14
     block
    -0.13
    POSITIVE LOGITS
    دÙħ
    0.16
    áºŃt
    0.15
    etler
    0.15
    genden
    0.15
    Unmount
    0.14
    ongan
    0.14
    ãĥªãĥ¼ãĤº
    0.14
     Æ°á»Ľc
    0.14
    rnek
    0.14
    ively
    0.14
    Act Density 0.008%

    No Known Activations