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

    Neuronpedia

    INDEX
    Explanations

    elements related to personal experiences and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .↵
    -0.30
    ).↵
    -0.25
    ãĢĤ↵
    -0.21
    .↵↵
    -0.20
    >.↵
    -0.20
    }.↵
    -0.20
    ".↵
    -0.19
    '.↵
    -0.19
    ."↵
    -0.19
    ().↵
    -0.18
    POSITIVE LOGITS
     zwar
    0.19
    ”ï¼Į
    0.16
     ìŀĪëĬĶëį°
    0.16
    ãĢij,
    0.15
    ãģĬãĤĬ
    0.15
     (),
    0.15
     _______,
    0.14
    AFX
    0.14
    ãĢĭï¼Į
    0.14
    !),
    0.14
    Act Density 0.961%

    No Known Activations