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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating confusion or ambiguity regarding ownership or responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avian
    -0.20
    adil
    -0.15
    etsk
    -0.15
    _SIG
    -0.14
    ,:,
    -0.14
     Trot
    -0.14
    ano
    -0.14
    istrat
    -0.13
    aceutical
    -0.13
    aven
    -0.13
    POSITIVE LOGITS
     nothing
    0.40
    nothing
    0.38
     Nothing
    0.36
    Nothing
    0.36
     NOTHING
    0.35
     nada
    0.31
     nichts
    0.29
     anything
    0.28
    anything
    0.26
     rien
    0.22
    Act Density 0.064%

    No Known Activations