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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and expressions of approval or disapproval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤĦãģ£ãģ¦
    -0.15
     VÅ¡ech
    -0.15
    мÑĸв
    -0.15
    yš
    -0.15
    ambre
    -0.15
    ylko
    -0.14
    Ñħодим
    -0.14
    ê¸Ī
    -0.14
    élé
    -0.14
    _TAC
    -0.13
    POSITIVE LOGITS
    inox
    0.18
    enheim
    0.17
     Podesta
    0.16
    bris
    0.15
     McK
    0.15
     tob
    0.15
    zb
    0.14
    illard
    0.14
     coal
    0.14
     quiz
    0.14
    Act Density 0.082%

    No Known Activations