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

    Neuronpedia

    INDEX
    Explanations

    patterns or structures in data representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ACHINE
    -0.16
    hle
    -0.15
    OLON
    -0.15
    credit
    -0.14
    agara
    -0.14
    ás
    -0.14
    ioned
    -0.14
    hl
    -0.13
     Sands
    -0.13
    foon
    -0.13
    POSITIVE LOGITS
    _DEPRECATED
    0.15
    auen
    0.15
     exc
    0.15
     Forward
    0.15
    elling
    0.14
    awei
    0.14
    ritz
    0.14
    born
    0.14
    affer
    0.14
     civ
    0.14
    Act Density 0.029%

    No Known Activations