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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistics related to research studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    96
    -0.22
    51
    -0.21
    52
    -0.21
    56
    -0.20
    57
    -0.20
    54
    -0.19
    49
    -0.19
    296
    -0.19
    97
    -0.19
    46
    -0.19
    POSITIVE LOGITS
    650
    0.39
    620
    0.37
    610
    0.37
    600
    0.36
    680
    0.35
    612
    0.35
    611
    0.35
    640
    0.35
    660
    0.35
    690
    0.35
    Act Density 0.143%

    No Known Activations