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

    Neuronpedia

    INDEX
    Explanations

    specific text that is being referenced in the document

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "reference" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilon
    -0.74
    alach
    -0.72
    Ģ
    -0.71
    ihad
    -0.70
    keye
    -0.70
    awar
    -0.70
    cffff
    -0.68
    ãĥ£
    -0.67
    omal
    -0.66
    icipated
    -0.66
    POSITIVE LOGITS
    enza
    0.80
    ENCE
    0.77
     thereto
    0.77
    minist
    0.74
    ibly
    0.71
    ="#
    0.71
    irect
    0.68
    reference
    0.68
     therein
    0.68
    ENC
    0.68
    Act Density 0.029%

    No Known Activations