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

    Neuronpedia

    INDEX
    Explanations

    superlative adjectives indicating extreme degrees, such as "most," "greatest," or "highest."

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of being the "most" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pload
    -0.79
    itan
    -0.70
    alid
    -0.66
    rish
    -0.64
    arter
    -0.63
    pton
    -0.60
    chrom
    -0.59
    icer
    -0.59
    icter
    -0.58
     tremend
    -0.58
    POSITIVE LOGITS
    likely
    0.99
    most
    0.93
    tenance
    0.92
     Helpful
    0.82
    etheless
    0.81
    quartered
    0.77
    egu
    0.75
    popular
    0.72
     Likely
    0.72
    bidden
    0.72
    Act Density 0.008%

    No Known Activations