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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a process of transformation or change

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "bec" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mble
    -0.84
     rug
    -0.70
    tsky
    -0.70
    DER
    -0.70
    packs
    -0.63
     cushion
    -0.60
     Harmon
    -0.60
     closure
    -0.59
     towed
    -0.58
     Abrams
    -0.57
    POSITIVE LOGITS
    oming
    1.06
    zek
    0.97
    esis
    0.96
    leans
    0.96
    erie
    0.93
    clair
    0.90
    bec
    0.89
    ault
    0.87
    asus
    0.85
    oin
    0.84
    Act Density 0.003%

    No Known Activations