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

    Neuronpedia

    INDEX
    Explanations

    clauses and definitions that emphasize key concepts or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Enums
    -0.15
    aban
    -0.15
    asher
    -0.14
     Ergebn
    -0.14
    alic
    -0.14
    iesen
    -0.14
     Pluto
    -0.13
     Kumar
    -0.13
    icken
    -0.13
    ivr
    -0.13
    POSITIVE LOGITS
     ones
    0.31
    ones
    0.20
     Ones
    0.19
     others
    0.19
    ONES
    0.16
    ulton
    0.16
     Hollow
    0.15
    çı
    0.15
    ABCDEFGHIJKLMNOP
    0.14
    ανδ
    0.14
    Act Density 0.122%

    No Known Activations