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

    Neuronpedia

    INDEX
    Explanations

    negative responses or dismissals

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    DeleteBehavior
    -0.73
    verwijspagina
    -0.72
     mijne
    -0.68
    RegistryLite
    -0.66
     سكانية
    -0.66
    ……"
    -0.65
    msgSender
    -0.63
    󠁳
    -0.63
     propOrder
    -0.63
    writeFieldEnd
    -0.62
    POSITIVE LOGITS
     moza
    0.61
     Eing
    0.60
     drap
    0.59
     Schu
    0.58
     StatelessWidget
    0.56
     placent
    0.56
     Marathi
    0.56
    rógeno
    0.56
    amata
    0.55
    Ei
    0.54
    Act Density 0.017%

    No Known Activations