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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases that imply connection or continuation in thought

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ippi
    -0.15
    vÄĽt
    -0.15
    uche
    -0.14
    жÑĥ
    -0.14
    IRA
    -0.14
    UDO
    -0.14
    gne
    -0.13
    imates
    -0.13
    onga
    -0.13
    rong
    -0.13
    POSITIVE LOGITS
     etc
    0.18
    etc
    0.17
     blah
    0.15
     sna
    0.14
    mani
    0.14
    rod
    0.13
    /string
    0.13
     Schneider
    0.13
    redo
    0.13
     dent
    0.13
    Act Density 0.096%

    No Known Activations