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

    Neuronpedia

    INDEX
    Explanations

    references to theft or stolen property

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     daß
    -0.60
    WithIOException
    -0.57
    NewUrlParser
    -0.53
     CURIAM
    -0.52
    kuuta
    -0.50
     Schluß
    -0.50
     Auft
    -0.49
    Lähteet
    -0.47
     ddelweddau
    -0.46
     keinerlei
    -0.46
    POSITIVE LOGITS
     stolen
    0.85
     Stolen
    0.70
     stole
    0.66
    Candidates
    0.64
    Stolen
    0.63
     Det
    0.62
     Candidates
    0.59
    Det
    0.57
    stolen
    0.57
     became
    0.57
    Act Density 0.207%

    No Known Activations