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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal or regulatory contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uner
    -0.16
    ture
    -0.15
     aspir
    -0.15
    asco
    -0.15
     absent
    -0.15
    sed
    -0.15
    ABCDEFGHIJKLMNOP
    -0.14
     buck
    -0.14
     congr
    -0.14
     abs
    -0.14
    POSITIVE LOGITS
    cen
    0.16
    pls
    0.15
    tember
    0.15
    ÅĽ
    0.14
    ceu
    0.14
    ëĭĪìĬ¤
    0.13
    nish
    0.13
    ÅĻÃŃ
    0.13
    ullets
    0.13
    nelle
    0.13
    Act Density 0.060%

    No Known Activations