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

    Neuronpedia

    INDEX
    Explanations

    locations or entities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    achus
    -0.76
    zzle
    -0.74
    terness
    -0.72
    rax
    -0.72
    ë
    -0.72
    opus
    -0.70
    onia
    -0.69
    leen
    -0.67
    owder
    -0.67
    ppe
    -0.66
    POSITIVE LOGITS
     findings
    1.01
     kinds
    0.99
     results
    0.96
     latter
    0.95
     developments
    0.93
     fellows
    0.93
     sorts
    0.92
     factors
    0.92
     entities
    0.92
     facts
    0.92
    Act Density 0.088%

    No Known Activations