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

    Neuronpedia

    INDEX
    Explanations

    terms related to rankings and positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ziej
    -0.16
     Raq
    -0.16
    ibling
    -0.15
    oro
    -0.15
    utsch
    -0.15
    nett
    -0.14
     fChain
    -0.14
    gili
    -0.14
    veau
    -0.14
    -www
    -0.14
    POSITIVE LOGITS
    ">//
    0.19
    elman
    0.15
    lander
    0.14
    tables
    0.14
    olders
    0.14
     dual
    0.14
    ritis
    0.13
     det
    0.13
     Sleeve
    0.13
    ji
    0.13
    Act Density 0.331%

    No Known Activations