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

    Neuronpedia

    INDEX
    Explanations

    phrases that encourage engagement with content, such as reading, watching, or checking out links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atters
    -0.15
    -Identifier
    -0.15
    soever
    -0.14
    ATTER
    -0.14
    entials
    -0.14
    erva
    -0.14
    èm
    -0.14
    ÑĢиÑĤ
    -0.13
    .ManyToMany
    -0.13
    zing
    -0.13
    POSITIVE LOGITS
     more
    0.39
     below
    0.28
     some
    0.28
     full
    0.26
    more
    0.25
    æĽ´å¤ļ
    0.25
     additional
    0.25
     all
    0.25
     previous
    0.25
     part
    0.24
    Act Density 0.097%

    No Known Activations