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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific words or character sequences related to names or places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _NC
    -0.15
    utron
    -0.14
    hoot
    -0.14
     leader
    -0.14
     Trading
    -0.14
     rally
    -0.14
     Rally
    -0.14
     dev
    -0.13
    rape
    -0.13
    erap
    -0.13
    POSITIVE LOGITS
    ungen
    0.19
    ouser
    0.18
    aker
    0.17
    PTY
    0.17
    abeth
    0.16
    sak
    0.16
    asser
    0.15
    bury
    0.15
    bian
    0.15
    unger
    0.14
    Act Density 0.053%

    No Known Activations