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

    Neuronpedia

    INDEX
    Explanations

    discussions related to subjects and topics in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ardo
    -0.17
    uder
    -0.17
    /preferences
    -0.16
    ushing
    -0.16
    ups
    -0.16
    ØŃÙĬ
    -0.15
    ppers
    -0.15
    lear
    -0.15
    undry
    -0.14
    ersh
    -0.14
    POSITIVE LOGITS
    ivity
    0.44
    ively
    0.40
     matter
    0.40
    matter
    0.35
    ivities
    0.34
    ive
    0.33
     Matter
    0.30
    ivism
    0.29
    ivist
    0.28
    IVE
    0.25
    Act Density 0.015%

    No Known Activations