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

    Neuronpedia

    INDEX
    Explanations

    capitalized names and terms related to authority or prominence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eman
    -0.17
     Twist
    -0.17
    olest
    -0.16
    ighton
    -0.16
    ext
    -0.15
    yg
    -0.15
    emann
    -0.15
    er
    -0.15
    zelf
    -0.15
    ksi
    -0.14
    POSITIVE LOGITS
    orca
    0.23
    enger
    0.21
    llll
    0.19
    engers
    0.18
    iance
    0.18
    tid
    0.18
    tach
    0.17
    ender
    0.17
    ure
    0.17
    acks
    0.17
    Act Density 0.005%

    No Known Activations