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

    Neuronpedia

    INDEX
    Explanations

    the concept of definiteness and certainty in statements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    er
    -0.63
    en
    -0.60
    cX
    -0.60
    Lear
    -0.58
    യ
    -0.57
    ed
    -0.56
     Scho
    -0.56
     crawls
    -0.56
    Baca
    -0.55
     rozum
    -0.55
    POSITIVE LOGITS
     BoxDecoration
    1.01
    LEncoder
    1.01
    definite
    0.95
    脚注の使い方
    0.95
     definite
    0.90
    ConstraintMaker
    0.90
    cydow
    0.88
    imentel
    0.86
    Identyfik
    0.85
    mybatisplus
    0.84
    Act Density 0.007%

    No Known Activations