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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "whi" and its related terms

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

    words starting with whip

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    afficheront
    -0.63
     AssemblyProduct
    -0.61
    帖最后由
    -0.59
     Infórmanos
    -0.58
    styleType
    -0.57
    ressee
    -0.57
     karen
    -0.56
    ctez
    -0.55
    findpost
    -0.55
    adaptiveStyles
    -0.54
    POSITIVE LOGITS
     Whi
    1.63
    Whi
    1.49
     whi
    1.41
    whi
    1.26
     Wiz
    0.90
     Whipple
    0.87
     wiz
    0.76
     whir
    0.76
     Whig
    0.71
    wiz
    0.70
    Act Density 0.008%

    No Known Activations