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

    Neuronpedia

    INDEX
    Explanations

    conjunctive phrases and connectors in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     {}.
    -0.07
     they
    -0.07
    gger
    -0.07
    fcn
    -0.07
    æ
    -0.07
    they
    -0.06
    ãİ
    -0.06
    Ùİج
    -0.06
     maka
    -0.06
    >').
    -0.06
    POSITIVE LOGITS
     with
    0.09
     because
    0.09
     given
    0.09
     after
    0.09
     thanks
    0.09
     knowing
    0.09
     having
    0.09
     without
    0.08
     despite
    0.08
     contrary
    0.08
    Act Density 0.079%

    No Known Activations