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

    Neuronpedia

    INDEX
    Explanations

    phrases related to numerical values and technical specifications

    oai_token-act-pair · gpt-3.5-turbo

    terms relevant to sports scoring and penalties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tranquil
    -0.65
    à¨
    -0.58
    lich
    -0.57
    hement
    -0.57
     sorts
    -0.57
     FOIA
    -0.56
    owship
    -0.56
     Wol
    -0.54
     Turing
    -0.53
     mosquito
    -0.53
    POSITIVE LOGITS
     increments
    0.80
     Tradable
    0.75
    imeters
    0.64
     Miko
    0.64
     verse
    0.61
    soDeliveryDate
    0.61
    ennial
    0.60
    anova
    0.59
    姫
    0.59
    oval
    0.58
    Act Density 0.634%

    No Known Activations