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

    Neuronpedia

    INDEX
    Explanations

    phrases that express generalizations or broad statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orry
    -0.16
    ender
    -0.16
    itos
    -0.16
    antlr
    -0.15
    iti
    -0.15
    assa
    -0.14
    itur
    -0.14
    itespace
    -0.14
    chg
    -0.14
    275
    -0.13
    POSITIVE LOGITS
    Ïĥη
    0.17
    éģ
    0.16
    <context
    0.15
    -speaking
    0.15
     generally
    0.15
    Guy
    0.14
    -ie
    0.14
    æĹ
    0.14
    lez
    0.14
    /general
    0.14
    Act Density 0.074%

    No Known Activations