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

    Neuronpedia

    INDEX
    Explanations

    occurrences of conjunctions and transitional phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ¬ł
    -0.19
    infeld
    -0.16
    ubern
    -0.15
     periodic
    -0.14
     occasional
    -0.14
    asser
    -0.14
     -*-č↵
    -0.14
    bsub
    -0.13
     Balk
    -0.13
    }č↵č↵č↵č↵
    -0.13
    POSITIVE LOGITS
     alongside
    0.18
    ium
    0.15
    oller
    0.15
    zig
    0.15
    ag
    0.14
    fy
    0.14
     Le
    0.14
     Miz
    0.13
    uss
    0.13
    este
    0.13
    Act Density 0.010%

    No Known Activations