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

    Neuronpedia

    INDEX
    Explanations

    patterns of conjunctions and sequencing in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĺ¯æĪij
    -0.15
     others
    -0.14
    \<^
    -0.14
    esk
    -0.14
    ÏĦία
    -0.13
     fortunately
    -0.13
    ÌĨ
    -0.13
    urf
    -0.13
    ultan
    -0.13
    hton
    -0.13
    POSITIVE LOGITS
     vo
    0.54
     guess
    0.46
     Vo
    0.43
    guess
    0.36
    Guess
    0.36
    vo
    0.35
    Vo
    0.35
     Guess
    0.35
     prest
    0.34
     VO
    0.32
    Act Density 0.297%

    No Known Activations