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

    Neuronpedia

    INDEX
    Explanations

    terms related to automation and its processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    entine
    -0.17
    acho
    -0.14
    ansa
    -0.14
    awner
    -0.14
     Pound
    -0.14
    aisy
    -0.13
     PSD
    -0.13
    pent
    -0.13
    oning
    -0.13
    Ps
    -0.13
    POSITIVE LOGITS
    enegro
    0.16
    stav
    0.15
    urtle
    0.15
    omor
    0.15
    efe
    0.15
    ÚĺÙĩ
    0.14
    ously
    0.14
    remen
    0.14
    .ali
    0.14
    znik
    0.14
    Act Density 0.010%

    No Known Activations