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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating previous experiences or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _NC
    -0.15
    irit
    -0.15
    anim
    -0.15
    esin
    -0.14
    orman
    -0.14
     Authority
    -0.14
    容
    -0.14
    alous
    -0.14
    kd
    -0.13
    isl
    -0.13
    POSITIVE LOGITS
    letcher
    0.14
    å£
    0.14
     lux
    0.14
    AREST
    0.14
    adena
    0.14
     reass
    0.14
     beck
    0.14
     abs
    0.14
    gia
    0.13
     reap
    0.13
    Act Density 0.013%

    No Known Activations