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

    Neuronpedia

    INDEX
    Explanations

    references to directed graphs and their ordering properties

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    __":
    -0.82
    TagMode
    -0.68
    AxisAlignment
    -0.67
    KommentareTeilen
    -0.66
    __':
    -0.66
    Portail
    -0.63
    IsContent
    -0.62
    DULE
    -0.62
    Hentet
    -0.61
     defaultstate
    -0.60
    POSITIVE LOGITS
     Tacitus
    0.58
     Undertaker
    0.57
     nutricional
    0.57
    perten
    0.56
    Geograf
    0.54
    ülés
    0.54
    hamilan
    0.53
    xaml
    0.52
     ͜ʖ
    0.51
    Anatom
    0.51
    Act Density 0.007%

    No Known Activations