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

    Neuronpedia

    INDEX
    Explanations

    text related to personal names or identifiers

    oai_token-act-pair · gpt-3.5-turbo

    specific suffixes or endings in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EStream
    -0.77
     pac
    -0.66
     proactive
    -0.65
     contrace
    -0.65
     feder
    -0.63
     normative
    -0.63
     sympathetic
    -0.60
    artifacts
    -0.60
     indict
    -0.60
     explanatory
    -0.60
    POSITIVE LOGITS
    ahs
    0.82
    iland
    0.82
    iken
    0.81
    opsis
    0.81
    tein
    0.80
    ornings
    0.77
    ott
    0.75
    akings
    0.74
    ake
    0.74
    ius
    0.74
    Act Density 0.199%

    No Known Activations