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

    Neuronpedia

    INDEX
    Explanations

    names or terms related to locations or people, particularly with the name "Ross."

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "Ro" followed by various letter combinations, indicating specific names or terms related to a particular context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uously
    -0.73
    Ö¼
    -0.73
    ately
    -0.65
     prelim
    -0.62
     mandate
    -0.60
    ateral
    -0.59
    redients
    -0.59
    OTOS
    -0.58
     temporal
    -0.58
    cause
    -0.58
    POSITIVE LOGITS
    velt
    1.07
     Rampage
    0.93
    heid
    0.92
    kefeller
    0.75
    coe
    0.71
    oke
    0.71
    wald
    0.71
    bery
    0.70
    eco
    0.67
    restling
    0.66
    Act Density 0.093%

    No Known Activations