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

    Neuronpedia

    INDEX
    Explanations

    combinations of various elements or concepts

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to combinations or integrations of different elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    taker
    -0.90
     repr
    -0.66
    seek
    -0.61
    fm
    -0.59
     Rampage
    -0.59
    ISTER
    -0.59
    KER
    -0.55
    gow
    -0.55
     Papa
    -0.55
     Shrine
    -0.55
    POSITIVE LOGITS
     dots
    0.93
     seamlessly
    0.88
    into
    0.84
    atin
    0.82
     disparate
    0.81
    igham
    0.80
     senses
    0.76
    ictive
    0.75
    ioxide
    0.74
    rette
    0.72
    Act Density 0.238%

    No Known Activations