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

    Neuronpedia

    INDEX
    Explanations

    key terms related to probabilities and assessments of situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÅĽnie
    -0.15
    å³°
    -0.15
    ucz
    -0.14
    vnÃŃ
    -0.14
    ahlen
    -0.14
     Alman
    -0.14
    Ä©a
    -0.14
     minded
    -0.14
    igkeit
    -0.14
    oÅĽci
    -0.14
    POSITIVE LOGITS
    _DISPATCH
    0.16
    ordes
    0.15
    adius
    0.14
    Äĩi
    0.14
    entes
    0.14
    _PKG
    0.13
    anka
    0.13
    ENTA
    0.13
    fur
    0.13
    /OR
    0.13
    Act Density 0.002%

    No Known Activations