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

    Neuronpedia

    INDEX
    Explanations

    specific prepositions and connectors in written statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    عاÙĨ
    -0.19
    zure
    -0.15
    enas
    -0.14
    IONS
    -0.14
    wish
    -0.14
    ponent
    -0.14
    Verb
    -0.13
    onaut
    -0.13
    cce
    -0.13
    ober
    -0.13
    POSITIVE LOGITS
    897
    0.16
     volume
    0.15
    allah
    0.15
    /form
    0.15
     illicit
    0.15
    annis
    0.14
    /il
    0.14
    ilim
    0.14
    antz
    0.14
    chai
    0.14
    Act Density 0.010%

    No Known Activations