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

    Neuronpedia

    INDEX
    Explanations

    percentages and their associated numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rd
    -0.15
     asc
    -0.15
    eden
    -0.15
    orth
    -0.15
    Bulk
    -0.14
    avigate
    -0.14
    ONA
    -0.14
    -0.14
    ackbar
    -0.14
    ELS
    -0.14
    POSITIVE LOGITS
    imenti
    0.15
     WaitForSeconds
    0.15
     Snyder
    0.14
    obre
    0.14
    circle
    0.14
    око
    0.14
    apesh
    0.14
    åľĪ
    0.14
    ourt
    0.14
    cko
    0.14
    Act Density 0.010%

    No Known Activations