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

    Neuronpedia

    INDEX
    Explanations

    terms related to methodology and methodological approaches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tob
    -0.14
     sco
    -0.14
     Tob
    -0.14
     Compet
    -0.14
    urtle
    -0.13
    lluminate
    -0.13
     Hindered
    -0.13
     competitor
    -0.13
    compet
    -0.13
    thur
    -0.12
    POSITIVE LOGITS
    Hack
    0.16
    Forge
    0.15
    å±ħ
    0.15
    antar
    0.15
     Execution
    0.15
    Meter
    0.14
    esar
    0.14
    ÄĽj
    0.14
    adc
    0.14
    urge
    0.14
    Act Density 0.008%

    No Known Activations