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

    Neuronpedia

    INDEX
    Explanations

    comparative expressions or phrases that indicate differences or contrasts

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

    comparisons using 'than'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    躇
    -0.71
     للمعارف
    -0.66
    gestone
    -0.63
    LLocation
    -0.60
    irut
    -0.59
     Clos
    -0.58
     Administrativna
    -0.58
    ſelf
    -0.58
    tagHelperRunner
    -0.57
    сай
    -0.56
    POSITIVE LOGITS
     than
    0.49
     fırs
    0.38
     dikembangkan
    0.38
    AnchorStyles
    0.37
     kuin
    0.37
     enemmän
    0.37
     tarvit
    0.36
     sekal
    0.36
     conmigo
    0.34
     eksemp
    0.33
    Act Density 0.033%

    No Known Activations