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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal thoughts and feelings, particularly in conversational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.82
     TextAppearance
    -0.76
     Normdatei
    -0.75
     الحره
    -0.72
    ografija
    -0.69
     raiſ
    -0.68
    Portail
    -0.66
    Cordialement
    -0.64
     виправивши
    -0.64
     صوتيه
    -0.63
    POSITIVE LOGITS
     '
    0.79
     hey
    0.76
    ว่า
    0.74
     saying
    0.72
     `
    0.68
     "
    0.68
    :
    0.63
     why
    0.62
     ‘
    0.61
    AddTagHelper
    0.61
    Act Density 0.151%

    No Known Activations