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

    Neuronpedia

    INDEX
    Explanations

    key terms and phrases related to bureaucratic language and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iggs
    -0.20
    halt
    -0.18
     presence
    -0.18
    itness
    -0.15
    agh
    -0.15
     Presence
    -0.15
     Fault
    -0.14
    presence
    -0.14
    esan
    -0.14
    anes
    -0.14
    POSITIVE LOGITS
    ragen
    0.16
    una
    0.15
    ĽĦ
    0.14
    ategorical
    0.14
    nerRadius
    0.14
    okus
    0.14
    pedia
    0.14
    cki
    0.14
    zew
    0.14
    ovice
    0.14
    Act Density 0.002%

    No Known Activations