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

    Neuronpedia

    INDEX
    Explanations

    citation or reference formats in academic writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roid
    -0.17
    rometer
    -0.16
    øj
    -0.16
    alles
    -0.16
    _REQUIRE
    -0.15
    dna
    -0.15
    ataka
    -0.15
    &action
    -0.14
    aison
    -0.14
     Ink
    -0.14
    POSITIVE LOGITS
    566
    0.16
    ieux
    0.15
     Treat
    0.15
     foc
    0.14
     Wich
    0.14
    urgy
    0.14
    pu
    0.14
    ugh
    0.14
    ioni
    0.14
    upo
    0.14
    Act Density 0.030%

    No Known Activations