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

    Neuronpedia

    INDEX
    Explanations

    references to significant news events or figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Extra
    -0.15
    .undefined
    -0.14
    ãĥĥãĤ«ãĥ¼
    -0.13
     Extras
    -0.13
    ãĥ³ãĥĩãĤ£
    -0.12
     Current
    -0.12
     Miscellaneous
    -0.12
     Simple
    -0.12
    avour
    -0.12
     vůbec
    -0.12
    POSITIVE LOGITS
     Isn
    0.23
     Didn
    0.23
     Could
    0.23
     Couldn
    0.22
     Wouldn
    0.22
     Finally
    0.20
     Doesn
    0.20
     vs
    0.20
     Was
    0.20
     Became
    0.20
    Act Density 0.197%

    No Known Activations