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

    Neuronpedia

    INDEX
    Explanations

    references to organizations and institutions related to health and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    indow
    -0.18
    ambi
    -0.15
    aj
    -0.15
    IEW
    -0.14
    CLA
    -0.13
    ange
    -0.13
     pac
    -0.13
    axy
    -0.13
    _AX
    -0.13
    amba
    -0.13
    POSITIVE LOGITS
    ynes
    0.16
    EEP
    0.15
    abbrev
    0.15
    Terr
    0.15
    rieve
    0.15
    :::
    0.15
    /tos
    0.14
    讯
    0.14
     Summon
    0.13
    eger
    0.13
    Act Density 0.128%

    No Known Activations