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

    Neuronpedia

    INDEX
    Explanations

    references to nouns and adjectives related to quality and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     seg
    -0.19
    roid
    -0.18
    ians
    -0.16
    ὶ
    -0.15
     Seg
    -0.15
    869
    -0.14
     Bull
    -0.14
    stri
    -0.14
    -bs
    -0.14
    509
    -0.14
    POSITIVE LOGITS
    acz
    0.19
     Lair
    0.16
    озна
    0.14
     jTextField
    0.14
    åIJ¦
    0.14
     changer
    0.13
    kelas
    0.13
     hale
    0.13
    hoff
    0.13
    ÑĤеÑĢи
    0.13
    Act Density 0.036%

    No Known Activations