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

    Neuronpedia

    INDEX
    Explanations

    concepts related to reciprocity and combination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sworth
    -0.15
    TERN
    -0.15
    ernaut
    -0.15
    ulled
    -0.15
    lle
    -0.14
    uzzle
    -0.14
    elman
    -0.14
    lak
    -0.14
    eldorf
    -0.14
    hawk
    -0.14
    POSITIVE LOGITS
    roc
    0.32
    (rec
    0.19
    ipro
    0.19
    city
    0.17
    ienda
    0.16
    ric
    0.16
    ipy
    0.16
    /rec
    0.15
    ros
    0.15
    Īĺ
    0.15
    Act Density 0.016%

    No Known Activations