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

    Neuronpedia

    INDEX
    Explanations

    phrases highlighting issues related to community accountability and policing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    êm
    -0.15
    _cpus
    -0.15
    rouw
    -0.15
    PropertyValue
    -0.14
    olley
    -0.14
    vů
    -0.14
    rong
    -0.14
    ê°IJ
    -0.14
    apis
    -0.13
     ÐļÑĢаÑĹна
    -0.13
    POSITIVE LOGITS
    0.17
     wine
    0.17
     music
    0.16
     alcohol
    0.16
     cheese
    0.16
     food
    0.16
     noise
    0.15
     chocolate
    0.15
     software
    0.14
    759
    0.14
    Act Density 0.278%

    No Known Activations