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

    Neuronpedia

    INDEX
    Explanations

    phrases that express causation or explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ussen
    -0.16
    zman
    -0.15
    zm
    -0.15
    unsch
    -0.15
    ANTED
    -0.15
    trag
    -0.14
    ÙĪغ
    -0.14
    reta
    -0.14
    ugin
    -0.14
    üssen
    -0.14
    POSITIVE LOGITS
    oice
    0.16
     Cf
    0.15
    weise
    0.15
    inos
    0.14
    '
    0.14
     emerging
    0.14
    oise
    0.14
     Regulations
    0.13
    enger
    0.13
     why
    0.13
    Act Density 0.094%

    No Known Activations