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

    Neuronpedia

    INDEX
    Explanations

    statistical methods related to post hoc analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    post hoc analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .*")]
    -0.45
    inella
    -0.41
    แน
    -0.39
    gdala
    -0.37
     opposite
    -0.36
    bondale
    -0.36
     فريبيس
    -0.36
    opposite
    -0.36
     Pulp
    -0.35
    urez
    -0.35
    POSITIVE LOGITS
     học
    2.45
     Học
    1.63
    học
    1.33
    Hoc
    0.89
    學
    0.88
    学
    0.81
    학
    0.80
     학
    0.75
    hoc
    0.74
     learns
    0.73
    Act Density 0.002%

    No Known Activations