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

    Neuronpedia

    INDEX
    Explanations

    conjunctions or linking phrases that create connections between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     etc
    -0.18
    ãĥ«ãĤ¯
    -0.15
    776
    -0.14
    oret
    -0.14
    ãģªãģ©
    -0.14
    dup
    -0.14
    334
    -0.14
     neither
    -0.14
    çŃī
    -0.14
    abet
    -0.13
    POSITIVE LOGITS
    phans
    0.16
     että
    0.15
     lẫn
    0.14
    /or
    0.14
    ients
    0.14
    à¹Ģหล
    0.14
    /OR
    0.14
    ackets
    0.14
    //{{
    0.14
    838
    0.14
    Act Density 0.075%

    No Known Activations