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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social dynamics and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uada
    -0.16
    olley
    -0.16
    hiba
    -0.16
    bic
    -0.16
    kre
    -0.15
    éĽ
    -0.14
     Din
    -0.14
    odied
    -0.14
    uggy
    -0.14
    rž
    -0.14
    POSITIVE LOGITS
     faster
    0.43
     fast
    0.42
    fast
    0.39
     speed
    0.39
     fastest
    0.36
     accelerated
    0.36
    -fast
    0.36
     Faster
    0.35
    speed
    0.35
    Fast
    0.35
    Act Density 0.217%

    No Known Activations