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

    Neuronpedia

    INDEX
    Explanations

    decimal numbers

    oai_token-act-pair · gpt-3.5-turbo

    numerical and statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     SET
    -0.77
     Ember
    -0.73
     Chop
    -0.72
     Tun
    -0.72
     SCP
    -0.72
     Mesa
    -0.70
     Dover
    -0.66
     Curiosity
    -0.66
     CAM
    -0.65
     Apollo
    -0.65
    POSITIVE LOGITS
    09
    0.98
    18
    0.97
    083
    0.93
    08
    0.93
    16
    0.93
    13
    0.93
    17
    0.93
    35
    0.92
    26
    0.92
    25
    0.92
    Act Density 0.092%

    No Known Activations