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

    Neuronpedia

    INDEX
    Explanations

    instances of violence and trauma

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     himself
    -0.69
    LookAnd
    -0.67
    EndContext
    -0.66
    felf
    -0.66
     насељу
    -0.65
    himself
    -0.65
    IndentedString
    -0.63
     المعيارى
    -0.62
     himſelf
    -0.62
    ImageContext
    -0.61
    POSITIVE LOGITS
     themselves
    1.42
    themselves
    1.16
     their
    1.15
    Their
    1.13
     Their
    1.10
    their
    1.04
     THEIR
    0.86
     själva
    0.85
     collectively
    0.83
     kteří
    0.83
    Act Density 1.087%

    No Known Activations