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

    Neuronpedia

    INDEX
    Explanations

    phrases related to advancement or development

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ig" within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Franch
    -0.75
     Sussex
    -0.64
     Despair
    -0.64
     Sparkle
    -0.61
    ãĥ¯ãĥ³
    -0.60
     Mub
    -0.60
     CSI
    -0.59
    etheless
    -0.59
    ervative
    -0.58
    ength
    -0.58
    POSITIVE LOGITS
    arette
    1.24
    abyte
    1.20
    arettes
    1.18
    gers
    1.17
    gered
    1.12
    rams
    1.09
    uana
    1.06
    glers
    1.04
    ging
    1.02
    uity
    1.01
    Act Density 0.041%

    No Known Activations