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

    Neuronpedia

    INDEX
    Explanations

    calls to action or prompts for signing up

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pline
    -0.16
    æ¨ĵ
    -0.16
    ufs
    -0.15
    arking
    -0.15
    tes
    -0.14
    acin
    -0.14
    edio
    -0.14
    æĬľ
    -0.14
    uvo
    -0.14
    ISTA
    -0.14
    POSITIVE LOGITS
    ificantly
    0.30
    atures
    0.29
    ificance
    0.26
    ificant
    0.26
    apore
    0.23
    ee
    0.22
    ees
    0.21
    ificado
    0.21
    atur
    0.21
    aling
    0.20
    Act Density 0.008%

    No Known Activations