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

    Neuronpedia

    INDEX
    Explanations

    terms related to simplicity or things that are simple

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to simplicity and minimalism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    affer
    -0.71
    reon
    -0.69
    inburgh
    -0.69
    vance
    -0.67
    CVE
    -0.66
    restling
    -0.66
    Ir
    -0.66
    ————————————————
    -0.66
     Monsanto
    -0.65
    apons
    -0.63
    POSITIVE LOGITS
    tons
    0.91
    wallet
    0.83
     simplicity
    0.80
    ified
    0.75
    ured
    0.74
    minded
    0.73
     straightforward
    0.73
     simple
    0.73
    simple
    0.72
    ctory
    0.71
    Act Density 0.030%

    No Known Activations