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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions involving exponents

    oai_token-act-pair · gpt-3.5-turbo

    mathematical symbols and references to music or film titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pec
    -0.83
    rek
    -0.77
    nels
    -0.76
    dogs
    -0.75
    aments
    -0.73
    ires
    -0.73
    azer
    -0.73
    stra
    -0.70
    lli
    -0.69
     bowls
    -0.69
    POSITIVE LOGITS
    ĸļ
    0.81
    assic
    0.68
     GOODMAN
    0.65
    SourceFile
    0.65
    swer
    0.64
     [|
    0.63
     Warden
    0.63
    halla
    0.63
    âĶĢâĶĢâĶĢâĶĢ
    0.62
     mM
    0.62
    Act Density 0.036%

    No Known Activations