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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating inclusivity or universality

    oai_token-act-pair · gpt-3.5-turbo

    connector words or phrases that indicate inclusivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rhodes
    -0.71
    Reloaded
    -0.69
    KC
    -0.66
     Lann
    -0.63
    Roll
    -0.61
    rawdownloadcloneembedreportprint
    -0.59
    GMT
    -0.59
     Alger
    -0.58
     reel
    -0.57
    BIL
    -0.56
    POSITIVE LOGITS
    atown
    0.71
    ativity
    0.70
    intent
    0.69
    aughtered
    0.68
    itud
    0.68
    otaur
    0.68
    ocene
    0.68
    science
    0.67
    eat
    0.67
    ividual
    0.67
    Act Density 0.485%

    No Known Activations