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

    Neuronpedia

    INDEX
    Explanations

    words related to intensity or importance

    oai_token-act-pair · gpt-3.5-turbo

    words related to various qualities or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mbuds
    -0.88
    udeb
    -0.80
    AMS
    -0.77
    soDeliveryDate
    -0.74
    MAR
    -0.72
    BIP
    -0.69
    OWS
    -0.68
    WT
    -0.67
    mith
    -0.65
    pin
    -0.65
    POSITIVE LOGITS
    ient
    1.27
    ial
    1.15
    ially
    1.07
    iency
    0.98
    ients
    0.86
    eers
    0.83
    estial
    0.80
    aily
    0.78
    ly
    0.77
    icut
    0.77
    Act Density 0.014%

    No Known Activations