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

    Neuronpedia

    INDEX
    Explanations

    terms related to conversations or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bers
    -0.17
    ildo
    -0.17
    esta
    -0.14
     Blank
    -0.14
    lessly
    -0.14
    ungan
    -0.14
    erten
    -0.14
    eba
    -0.14
    eval
    -0.14
     Gone
    -0.14
    POSITIVE LOGITS
    ational
    0.28
    acional
    0.20
    ely
    0.19
    ing
    0.19
    azioni
    0.19
    ATIONAL
    0.18
    /Dk
    0.17
    idge
    0.17
    RAD
    0.16
    ecast
    0.16
    Act Density 0.006%

    No Known Activations