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

    Neuronpedia

    INDEX
    Explanations

    quantitative values or measurements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to approximate quantities or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ters
    -0.89
    ieu
    -0.81
    woods
    -0.77
    oli
    -0.75
    enders
    -0.72
    ny
    -0.71
    oly
    -0.71
    neys
    -0.70
    brow
    -0.66
    Reviewer
    -0.66
    POSITIVE LOGITS
    Ĥİ
    0.85
    atility
    0.74
     âĸĪ
    0.73
    roximately
    0.73
     Approximately
    0.72
     midway
    0.70
     200
    0.70
    capacity
    0.70
     175
    0.69
    ptoms
    0.69
    Act Density 0.015%

    No Known Activations