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

    Neuronpedia

    INDEX
    Explanations

    references to norms, standards, and typical behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     actual
    -0.16
     particular
    -0.15
     entire
    -0.14
    itch
    -0.14
     Katrina
    -0.14
    åĪ¥
    -0.14
    cap
    -0.14
     Jul
    -0.14
    lio
    -0.14
    actual
    -0.14
    POSITIVE LOGITS
     suspects
    0.35
     fare
    0.31
    /common
    0.21
     suspect
    0.21
    -issue
    0.21
    /default
    0.20
    -standard
    0.20
    üstü
    0.19
    fare
    0.19
     stuff
    0.18
    Act Density 0.138%

    No Known Activations