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

    Neuronpedia

    INDEX
    Explanations

    references to numerical data or citation metrics in academic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edo
    -0.20
    eros
    -0.15
    oje
    -0.15
    ught
    -0.15
     zig
    -0.14
    /www
    -0.14
    zier
    -0.13
    presso
    -0.13
    ook
    -0.12
    uesta
    -0.12
    POSITIVE LOGITS
    quat
    0.18
    uzzi
    0.15
    enco
    0.15
    idel
    0.14
    -inline
    0.14
    belt
    0.14
    ovsky
    0.14
    aller
    0.13
    loquent
    0.13
    jad
    0.13
    Act Density 0.005%

    No Known Activations