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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "on" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OA
    -0.18
    anded
    -0.17
    etz
    -0.16
    ivos
    -0.15
    xit
    -0.14
    -line
    -0.14
    odont
    -0.14
    vil
    -0.14
    inu
    -0.14
    crest
    -0.14
    POSITIVE LOGITS
     paper
    0.24
     defense
    0.23
     offense
    0.21
    ç´Ļ
    0.20
    纸
    0.19
     offence
    0.18
     defence
    0.18
    -paper
    0.18
     turf
    0.17
    Ŀ
    0.17
    Act Density 0.031%

    No Known Activations