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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "and" as a connective

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lobber
    -0.15
    lero
    -0.14
    adia
    -0.14
    ivities
    -0.13
    esses
    -0.13
    iano
    -0.13
    ге
    -0.13
    και
    -0.13
    iples
    -0.13
    icus
    -0.13
    POSITIVE LOGITS
    rez
    0.17
    elage
    0.16
    eni
    0.14
     ÎijÎł
    0.14
    ziej
    0.14
    reeze
    0.14
    ohana
    0.14
    Arrow
    0.14
     pParent
    0.14
    ÏĦÏĥ
    0.14
    Act Density 0.055%

    No Known Activations