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

    Neuronpedia

    INDEX
    Explanations

    key terms related to educational systems and oversight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wake
    -0.17
    stad
    -0.16
    neau
    -0.16
    '=>['
    -0.15
    assis
    -0.15
     Leap
    -0.14
    æī«
    -0.14
    Ä°n
    -0.14
    aos
    -0.14
    imu
    -0.14
    POSITIVE LOGITS
    adden
    0.16
    irsch
    0.15
    ordin
    0.14
    rcode
    0.13
    imoto
    0.13
    ulp
    0.13
     Skill
    0.13
    _ALIGNMENT
    0.13
    ecess
    0.13
    epar
    0.13
    Act Density 0.004%

    No Known Activations