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

    Neuronpedia

    INDEX
    Explanations

    comparisons between subjects or data sets

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

    comparing to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.50
     handel
    -0.46
    claves
    -0.43
    expandindo
    -0.43
    AndEndTag
    -0.41
     doch
    -0.40
    localctx
    -0.39
    HtmlAttribute
    -0.38
     intStringLen
    -0.38
    omenclature
    -0.38
    POSITIVE LOGITS
     compared
    0.63
     compare
    0.61
     Compare
    0.60
     compares
    0.59
    Compare
    0.59
    compared
    0.59
     dibandingkan
    0.55
     dibanding
    0.54
    ⓧ
    0.54
     resemble
    0.52
    Act Density 0.050%

    No Known Activations