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

    Neuronpedia

    INDEX
    Explanations

    themes of powerlessness and moral dilemmas in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fauc
    -0.15
    astle
    -0.15
    adies
    -0.14
    asu
    -0.14
     forc
    -0.14
    raç
    -0.14
     Saud
    -0.13
    нка
    -0.13
    ä
    -0.13
     automáticamente
    -0.13
    POSITIVE LOGITS
    CLR
    0.15
     McCorm
    0.15
    jeta
    0.14
    ammo
    0.14
     (“
    0.14
    ILT
    0.14
    寸
    0.13
    ìĬ¤íĨł
    0.13
    607
    0.13
    Ħ件
    0.13
    Act Density 0.200%

    No Known Activations