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

    Neuronpedia

    INDEX
    Explanations

    abbreviations or initialisms related to different subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odore
    -0.17
    vik
    -0.15
    ater
    -0.15
    æĥł
    -0.15
    otope
    -0.15
    icz
    -0.15
    dney
    -0.15
    essional
    -0.15
    opher
    -0.14
    GetMethod
    -0.14
    POSITIVE LOGITS
     propos
    0.21
    ube
    0.20
    vertisement
    0.19
    udios
    0.18
    prox
    0.18
    idth
    0.17
    uido
    0.17
     dv
    0.17
    alysis
    0.16
    finity
    0.16
    Act Density 0.110%

    No Known Activations