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

    Neuronpedia

    INDEX
    Explanations

    phrases about misrepresentation and social justice issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autorytatywna
    -1.10
    DockStyle
    -1.10
    MigrationBuilder
    -0.99
    =$?
    -0.95
     disambiguazione
    -0.95
     مشين
    -0.94
    SequentialGroup
    -0.94
    حوالہ
    -0.94
    脚注の使い方
    -0.92
    __":
    -0.90
    POSITIVE LOGITS
     truly
    0.49
     ceea
    0.42
     typically
    0.40
     Typically
    0.40
    By
    0.39
    For
    0.39
     often
    0.39
    ↵↵
    0.39
    janje
    0.39
     traditionally
    0.38
    Act Density 0.447%

    No Known Activations