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

    Neuronpedia

    INDEX
    Explanations

    words related to linguistics and the study of language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ertas
    -0.16
    ÑħÑĥ
    -0.15
    /gtest
    -0.14
    pler
    -0.14
    ipc
    -0.14
     gó
    -0.14
    AYER
    -0.14
     åī
    -0.14
    ctors
    -0.14
    ayer
    -0.14
    POSITIVE LOGITS
    nom
    0.15
     bomb
    0.14
     gro
    0.14
     gas
    0.14
     oct
    0.14
    amam
    0.14
     nominal
    0.14
    аÑĢÑħ
    0.14
    lor
    0.13
    anon
    0.13
    Act Density 0.002%

    No Known Activations