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

    Neuronpedia

    INDEX
    Explanations

    identifiers and numerical data related to metrics and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Û³Ûµ
    -0.17
     Kendrick
    -0.17
     pent
    -0.16
    825
    -0.16
    815
    -0.15
    atat
    -0.15
    965
    -0.15
    925
    -0.14
    275
    -0.14
     Pent
    -0.14
    POSITIVE LOGITS
    490
    0.35
    190
    0.35
    130
    0.34
    460
    0.33
    390
    0.33
    180
    0.33
    430
    0.32
    230
    0.32
    240
    0.32
    440
    0.32
    Act Density 0.090%

    No Known Activations