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

    Neuronpedia

    INDEX
    Explanations

    patterns related to comparisons and variations in approaches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LabelTagHelper
    -0.68
    θεια
    -0.67
    ntlet
    -0.62
    AutoScaleMode
    -0.57
    __":
    -0.54
    <?
    -0.52
    toPromise
    -0.51
    enderror
    -0.50
    ⓧ
    -0.50
     للمعارف
    -0.49
    POSITIVE LOGITS
     different
    3.37
    different
    2.96
    Different
    2.82
     Different
    2.81
     DIFFERENT
    2.50
     diferente
    2.34
     differently
    2.22
     diferentes
    2.19
     différent
    2.16
    不同的
    2.15
    Act Density 1.210%

    No Known Activations