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

    Neuronpedia

    INDEX
    Explanations

    actions and verbs that imply taking care of oneself and others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (“
    -0.13
    \↵
    -0.12
    галÑĸ
    -0.12
    ]={↵
    -0.12
     cazzo
    -0.12
    vido
    -0.12
    ürnberg
    -0.12
    @gmail
    -0.12
     ÑĢеÑģ
    -0.12
     Sesso
    -0.11
    POSITIVE LOGITS
    ddb
    0.14
    feb
    0.13
    acf
    0.13
    [email
    0.13
    pch
    0.12
     же
    0.12
    ccd
    0.12
    ddf
    0.12
    afd
    0.11
     DialogInterface
    0.11
    Act Density 3.311%

    No Known Activations