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

    Neuronpedia

    INDEX
    Explanations

    concepts related to uniformity and consistency in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.46
    허
    -0.42
    zzleHttp
    -0.38
    intval
    -0.38
     Unsc
    -0.37
     gra
    -0.37
     quer
    -0.37
    <%=
    -0.36
    ampingi
    -0.36
     Frank
    -0.35
    POSITIVE LOGITS
     unified
    1.07
     unify
    1.01
    統一
    0.97
     unifying
    0.93
    统一
    0.93
     unification
    0.90
     einheit
    0.90
    unified
    0.89
    Unified
    0.89
     Unified
    0.89
    Act Density 0.581%

    No Known Activations