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

    Neuronpedia

    INDEX
    Explanations

    references to acts of murder and logging activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    makeConstraints
    -0.92
     Didi
    -0.85
     Salv
    -0.75
    πως
    -0.74
     représ
    -0.73
     Prid
    -0.72
     laine
    -0.71
    wakili
    -0.71
    rifugal
    -0.69
     Delf
    -0.69
    POSITIVE LOGITS
    rungsseite
    0.82
    ecture
    0.79
    imageio
    0.74
    inheritDoc
    0.74
    Octo
    0.73
     Kasper
    0.71
     Schröder
    0.71
     Octo
    0.71
    erus
    0.71
     logger
    0.70
    Act Density 0.065%

    No Known Activations