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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing equivalence or correspondence

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    rdı
    -0.80
     CreateTagHelper
    -0.77
    Composable
    -0.74
     <<<<<<<<<<<<<<
    -0.71
    Obrázky
    -0.69
    balleur
    -0.68
    addGroup
    -0.68
    Externí
    -0.67
     humains
    -0.67
     mellan
    -0.66
    POSITIVE LOGITS
     coincide
    1.13
     coincides
    1.04
     coinc
    1.01
     coincided
    0.81
     trùng
    0.79
     Palladium
    0.79
     officio
    0.77
     coincidence
    0.72
     coincident
    0.72
     Curs
    0.71
    Act Density 0.005%

    No Known Activations