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

    Neuronpedia

    INDEX
    Explanations

    instances of reports or mentions of happenings or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stuff
    -0.17
    stuff
    -0.15
    ãĥ«ãĥķ
    -0.14
     ë²Ķ
    -0.14
    arshal
    -0.13
    ارÙĩ
    -0.13
    .ax
    -0.13
    057
    -0.13
     внимание
    -0.13
    ien
    -0.13
    POSITIVE LOGITS
     reports
    0.34
     indications
    0.28
     Reports
    0.26
     signs
    0.26
    reports
    0.26
     suggestions
    0.25
    Reports
    0.23
     indication
    0.22
     fears
    0.22
     suggestion
    0.22
    Act Density 0.051%

    No Known Activations