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

    Neuronpedia

    INDEX
    Explanations

    repeated uses of the word "they" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reme
    -0.18
    remely
    -0.15
    apis
    -0.15
    ect
    -0.14
    .cmd
    -0.14
    HING
    -0.14
     Blo
    -0.14
    olley
    -0.14
    ãĤ«ãĥ¼
    -0.13
    ENDED
    -0.13
    POSITIVE LOGITS
    ảnh
    0.16
    _FATAL
    0.16
     Oaks
    0.15
    imers
    0.14
     Jeg
    0.14
    lobal
    0.14
    formance
    0.14
     lô
    0.14
    untime
    0.13
    VC
    0.13
    Act Density 0.500%

    No Known Activations