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

    Neuronpedia

    INDEX
    Explanations

    Latin characters, possibly symbolizing some form of emphasis or highlighting

    oai_token-act-pair · gpt-3.5-turbo

    the symbol 'Ŀ' or similar special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     controvers
    -0.89
     overloaded
    -0.83
     targeted
    -0.81
     calcul
    -0.81
     mushroom
    -0.81
     ende
    -0.80
     warr
    -0.79
     tricked
    -0.79
     habit
    -0.77
     camoufl
    -0.77
    POSITIVE LOGITS
    ï¸ı
    1.29
    ¯
    1.06
    laughs
    1.01
    ï¸
    1.00
    ÃĽ
    0.94
    dj
    0.90
    âĻ¦
    0.90
    Brend
    0.89
    Pause
    0.89
    laughter
    0.89
    Act Density 0.160%

    No Known Activations