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

    Neuronpedia

    INDEX
    Explanations

    interactions and emotional responses among characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alse
    -0.17
    czy
    -0.16
    ISTA
    -0.15
    arie
    -0.14
    alia
    -0.14
    falls
    -0.14
    lets
    -0.14
    ibble
    -0.14
    _:*
    -0.14
    ubl
    -0.14
    POSITIVE LOGITS
    iem
    0.21
    å¿«
    0.16
    openhagen
    0.15
    atro
    0.15
    ť
    0.15
     Habit
    0.14
    ONO
    0.14
     ÅĽw
    0.14
    eros
    0.14
    -open
    0.14
    Act Density 0.126%

    No Known Activations