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

    Neuronpedia

    INDEX
    Explanations

    specific scientific publications and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anners
    -0.15
    /gin
    -0.15
    atk
    -0.15
     Meh
    -0.14
     Mess
    -0.14
     quar
    -0.14
    ETER
    -0.14
    eyse
    -0.13
    200
    -0.13
    oller
    -0.13
    POSITIVE LOGITS
     Nature
    0.22
    Nature
    0.20
    npj
    0.19
     Nat
    0.18
    Nat
    0.18
     nature
    0.17
    nature
    0.17
    ATURE
    0.15
    ature
    0.15
     incor
    0.15
    Act Density 0.097%

    No Known Activations