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

    Neuronpedia

    INDEX
    Explanations

    metrics and percentages related to statistical changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ENU
    -0.15
    kup
    -0.15
    ÑĢан
    -0.14
     Hoover
    -0.13
    izzo
    -0.13
    sson
    -0.13
    dÄĽl
    -0.13
    irtschaft
    -0.13
    podob
    -0.13
    .ToArray
    -0.13
    POSITIVE LOGITS
     increase
    0.66
     Increase
    0.54
    increase
    0.53
     increases
    0.51
     decrease
    0.51
     rise
    0.47
    Increase
    0.46
    _increase
    0.42
     drop
    0.41
     decline
    0.40
    Act Density 0.354%

    No Known Activations