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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating purpose or suitability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bes
    -0.16
    cka
    -0.16
    addock
    -0.16
    bec
    -0.15
    orca
    -0.15
    auc
    -0.15
    miss
    -0.15
     glut
    -0.14
     as
    -0.14
    zx
    -0.14
    POSITIVE LOGITS
    Äįin
    0.16
     Sound
    0.15
    Å¡ÃŃ
    0.15
    _finalize
    0.15
     Angel
    0.14
    estr
    0.14
     fitte
    0.14
     ryb
    0.14
    маз
    0.14
     ÙĪات
    0.14
    Act Density 0.005%

    No Known Activations