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

    Neuronpedia

    INDEX
    Explanations

    references to well-known or notable subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illères
    -0.62
    stridium
    -0.61
     Polis
    -0.60
     zlo
    -0.59
    Prun
    -0.59
     Serap
    -0.58
    ContentAlignment
    -0.58
    脚注の使い方
    -0.58
     spie
    -0.58
    曖昧さ回避
    -0.58
    POSITIVE LOGITS
    famous
    1.26
     famous
    1.25
     Famous
    1.20
    Famous
    1.09
     famously
    1.07
     famosa
    1.07
     famoso
    1.06
     notorious
    1.04
     infamous
    1.04
    著名的
    1.01
    Act Density 0.146%

    No Known Activations