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

    Neuronpedia

    INDEX
    Explanations

    mentions of personal opinions or viewpoints expressed by individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "views" and related expressions of opinion or perspective

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mamm
    -0.78
    enary
    -0.72
    ALL
    -0.68
    moon
    -0.66
    eri
    -0.63
    trap
    -0.63
    Sequ
    -0.60
    enum
    -0.60
    amaz
    -0.58
    dry
    -0.58
    POSITIVE LOGITS
    cape
    0.94
    chool
    0.94
    hops
    0.91
    omething
    0.87
    hip
    0.87
     opinions
    0.86
    yip
    0.84
     beliefs
    0.84
    paces
    0.82
    afety
    0.81
    Act Density 0.059%

    No Known Activations