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

    Neuronpedia

    INDEX
    Explanations

    instances of decision-making and approval processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abad
    -0.15
     Tits
    -0.14
    943
    -0.14
    à¥įदर
    -0.14
    DY
    -0.14
    ogi
    -0.14
     bÃŃ
    -0.14
    ocz
    -0.14
    ollo
    -0.14
    ocket
    -0.14
    POSITIVE LOGITS
    ÑĢаÑħов
    0.17
    ruba
    0.15
    assy
    0.15
     Levine
    0.15
    è´
    0.14
    imet
    0.14
     Levin
    0.14
    lider
    0.14
    antee
    0.14
     credit
    0.14
    Act Density 0.273%

    No Known Activations