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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating relationships or positions within a context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     per
    -0.66
     Per
    -0.60
     a
    -0.59
     an
    -0.57
     van
    -0.55
    per
    -0.54
     D
    -0.53
    ing
    -0.53
     U
    -0.53
    Pav
    -0.52
    POSITIVE LOGITS
    ValueStyle
    0.91
     '\\;'
    0.90
     ―――――
    0.87
     MainAxisSize
    0.82
     myſelf
    0.82
    رشف
    0.81
     >=",
    0.80
     ་་
    0.76
     ――――――――
    0.76
     crdi
    0.76
    Act Density 0.199%

    No Known Activations