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

    Neuronpedia

    INDEX
    Explanations

    references to research methodologies and data sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urtle
    -0.17
    .tt
    -0.16
    'gc
    -0.16
    ropa
    -0.15
    urf
    -0.14
    fter
    -0.14
    _submit
    -0.14
    Submitted
    -0.14
    .Counter
    -0.14
    ULK
    -0.14
    POSITIVE LOGITS
     Wave
    0.38
     waves
    0.35
     Waves
    0.35
     wave
    0.34
    Wave
    0.29
    waves
    0.29
    wave
    0.28
    -wave
    0.28
    _wave
    0.25
     Panel
    0.24
    Act Density 0.013%

    No Known Activations