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

    Neuronpedia

    INDEX
    Explanations

    words that indicate personal involvement or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hawkins
    -0.16
    senal
    -0.16
    íĮĶ
    -0.15
    ÙĬÙĥÙĬ
    -0.15
    åĥį
    -0.15
    Interpolator
    -0.14
    ERC
    -0.14
    ResultsController
    -0.14
    opp
    -0.14
    -cross
    -0.14
    POSITIVE LOGITS
    uden
    0.16
    urm
    0.16
    oom
    0.15
    asic
    0.14
    uster
    0.14
    ued
    0.14
    ounder
    0.14
     ver
    0.14
    uzu
    0.14
    omo
    0.14
    Act Density 0.004%

    No Known Activations