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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to statistics or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HX
    -0.15
    unal
    -0.15
    roulette
    -0.14
    lopedia
    -0.13
    ongan
    -0.13
    rosse
    -0.13
     çok
    -0.13
    anton
    -0.13
     Much
    -0.13
    ustil
    -0.13
    POSITIVE LOGITS
     shy
    0.47
     short
    0.39
     behind
    0.35
     removed
    0.34
     above
    0.32
     below
    0.32
     ahead
    0.31
     away
    0.31
     apart
    0.30
     Short
    0.26
    Act Density 0.071%

    No Known Activations