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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ke activity

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to visual elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.71
    ibly
    -0.59
    shire
    -0.59
     indefinitely
    -0.58
     including
    -0.58
    enegger
    -0.58
     Tradable
    -0.57
     Digest
    -0.55
    itud
    -0.55
     comprising
    -0.54
    POSITIVE LOGITS
    lp
    1.32
    wl
    1.30
    ller
    1.24
    gger
    1.13
    pler
    1.12
    jriwal
    1.11
    llers
    1.10
    ez
    1.07
    gged
    1.07
    lly
    1.06
    Act Density 0.041%

    No Known Activations