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

    Neuronpedia

    INDEX
    Explanations

    compound adjectives often related to design or functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chemas
    -0.17
    arra
    -0.16
    asal
    -0.14
    reau
    -0.14
     Spirits
    -0.14
    ilos
    -0.14
    gan
    -0.13
    istence
    -0.13
    elts
    -0.13
     θÎŃ
    -0.13
    POSITIVE LOGITS
    ve
    0.18
    luk
    0.17
    rob
    0.16
    /-
    0.16
    ihad
    0.15
    uced
    0.15
    jÃŃm
    0.15
    Kit
    0.15
    ibur
    0.14
    pson
    0.14
    Act Density 0.162%

    No Known Activations