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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize the result or outcome of an action or situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     >=",
    -0.75
    Hentet
    -0.61
     بيها
    -0.57
     Beauchamp
    -0.56
     Appleton
    -0.56
     INGRED
    -0.53
    >{@
    -0.53
    bastien
    -0.53
    xious
    -0.52
    awtextra
    -0.52
    POSITIVE LOGITS
     Оно
    0.84
     оно
    0.82
     its
    0.79
     itself
    0.70
     it
    0.63
    它
    0.62
     Its
    0.61
     它
    0.59
    Its
    0.57
     themselves
    0.56
    Act Density 0.150%

    No Known Activations