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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sak
    -0.15
    overrides
    -0.15
    artifact
    -0.14
    stk
    -0.14
    plete
    -0.14
    agu
    -0.14
    ests
    -0.14
     Byrne
    -0.14
    Indented
    -0.14
    rou
    -0.14
    POSITIVE LOGITS
    awn
    0.21
    onna
    0.21
    isha
    0.19
    rece
    0.19
    undra
    0.18
    vious
    0.17
    onda
    0.17
    asha
    0.17
    ilee
    0.17
    iece
    0.16
    Act Density 0.180%

    No Known Activations