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

    Neuronpedia

    INDEX
    Explanations

    words related to abundance, excess, or large quantities

    oai_token-act-pair · gpt-3.5-turbo

    words that denote qualities or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UTC
    -0.68
     tabl
    -0.68
    VP
    -0.66
    ICAN
    -0.66
    URA
    -0.66
    ARP
    -0.65
     largeDownload
    -0.65
    IPP
    -0.64
    arations
    -0.64
     Roth
    -0.64
    POSITIVE LOGITS
    ious
    1.47
    ness
    1.18
    nesses
    1.06
    ity
    0.97
    lihood
    0.97
    iously
    0.93
    theless
    0.85
    vous
    0.84
    liness
    0.82
    lly
    0.78
    Act Density 0.018%

    No Known Activations