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

    Neuronpedia

    INDEX
    Explanations

    references to legal proceedings and courtroom scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Alarm
    -0.16
     Patron
    -0.15
    kü
    -0.15
    rotch
    -0.14
     plunge
    -0.14
    alar
    -0.14
    ceptive
    -0.14
    ëł¹
    -0.14
    änger
    -0.14
    atak
    -0.13
    POSITIVE LOGITS
     trial
    0.45
    trial
    0.35
     court
    0.35
     charges
    0.34
     trials
    0.33
     case
    0.32
     conviction
    0.30
     cases
    0.30
     Trial
    0.30
    åºŃ
    0.30
    Act Density 0.822%

    No Known Activations