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

    Neuronpedia

    INDEX
    Explanations

    words related to degree modifiers indicating a balance or limit between two extremes

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating moderation or balance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hyde
    -0.89
    ãĥ¼ãĥĨãĤ£
    -0.83
    iens
    -0.72
    otte
    -0.70
     Sutherland
    -0.66
    ibel
    -0.65
    arium
    -0.64
    inators
    -0.64
    orians
    -0.63
    icipated
    -0.63
    POSITIVE LOGITS
     much
    0.81
     noticeable
    0.80
     detectable
    0.75
     risky
    0.71
     flashy
    0.70
     expensive
    0.70
     obvious
    0.69
     conspicuous
    0.69
     len
    0.69
     busy
    0.69
    Act Density 0.019%

    No Known Activations