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

    Neuronpedia

    INDEX
    Explanations

    technical terms and jargon related to specific fields or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pga
    -0.19
    gie
    -0.17
    insic
    -0.16
    rak
    -0.15
     mastur
    -0.14
    ãĥ¼ãĥ
    -0.14
    odel
    -0.14
     Ùĥر
    -0.14
    ossier
    -0.14
    cel
    -0.14
    POSITIVE LOGITS
    -like
    0.27
    -style
    0.25
    -type
    0.22
    ing
    0.21
    -esque
    0.21
     style
    0.20
    like
    0.19
     technique
    0.18
    å¼ı
    0.18
     type
    0.17
    Act Density 0.062%

    No Known Activations