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

    Neuronpedia

    INDEX
    Explanations

    situations where avoidance is recommended or discussed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abyrinth
    -0.15
    ØŃ
    -0.15
    ÑĤÑĮ
    -0.15
    ãģ¾ãģ¾
    -0.15
    extView
    -0.14
    lements
    -0.14
    ileo
    -0.14
    enko
    -0.14
    گذ
    -0.14
    atura
    -0.14
    POSITIVE LOGITS
    ance
    0.28
     altogether
    0.25
     pitfalls
    0.20
    /mit
    0.20
    ably
    0.18
    ANCE
    0.18
    /min
    0.18
    ances
    0.17
    ant
    0.16
    /null
    0.16
    Act Density 0.029%

    No Known Activations