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

    Neuronpedia

    INDEX
    Explanations

    names of people

    oai_token-act-pair · gpt-3.5-turbo

    specific names and identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Gra
    -0.79
     Mount
    -0.76
     Gaw
    -0.76
     Warfare
    -0.73
    è»
    -0.72
    ç«
    -0.72
    URES
    -0.72
     Territories
    -0.72
     Pegasus
    -0.72
     MER
    -0.72
    POSITIVE LOGITS
    ins
    1.56
    in
    1.53
    IN
    1.40
    inian
    1.37
    inis
    1.37
    ino
    1.33
    ini
    1.30
    ÃŃn
    1.29
    inn
    1.28
    inos
    1.24
    Act Density 0.158%

    No Known Activations