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

    Neuronpedia

    INDEX
    Explanations

    words indicating capability, visibility, and perceptibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    croft
    -0.17
    åĻ
    -0.16
    itz
    -0.16
    avery
    -0.15
     Claw
    -0.14
     ÎļαÏĦηγοÏģία
    -0.14
    324
    -0.14
    aver
    -0.14
    plex
    -0.14
    dex
    -0.14
    POSITIVE LOGITS
    .alloc
    0.15
     Verfüg
    0.15
    å°ļ
    0.14
    asionally
    0.14
    ropri
    0.14
    ,Yes
    0.14
    undi
    0.13
    æ´ĭ
    0.13
    uids
    0.13
    IClient
    0.13
    Act Density 0.041%

    No Known Activations