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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting typically used in mathematical expressions and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nbsp
    -0.17
    emat
    -0.15
     somew
    -0.15
    391
    -0.14
    earch
    -0.14
     kole
    -0.14
    erb
    -0.14
     vur
    -0.13
    ould
    -0.13
     hybrids
    -0.13
    POSITIVE LOGITS
    rm
    0.20
    script
    0.18
    ssf
    0.17
    #ad
    0.15
    ãĥĭãĤ¢
    0.15
     rm
    0.15
    isas
    0.15
    ãĥ¼ãĥ
    0.15
    /script
    0.14
    INU
    0.14
    Act Density 0.113%

    No Known Activations