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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to quantitative measurements and comparisons in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dafx
    -0.39
    reject
    -0.37
    Exclude
    -0.36
     tranſ
    -0.35
    stop
    -0.34
     Bersama
    -0.34
     Pourtant
    -0.34
     exer
    -0.33
     DIEGO
    -0.33
     bords
    -0.33
    POSITIVE LOGITS
    ViewFeatures
    0.71
     ratio
    0.60
     يتيمه
    0.57
     שוליים
    0.55
     proportionate
    0.55
     Ratios
    0.53
     Ratio
    0.52
     ratios
    0.52
    比例
    0.51
     RATIO
    0.51
    Act Density 0.500%

    No Known Activations