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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms related to regulatory measures and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izoph
    -0.72
     colourful
    -0.71
    eme
    -0.70
     flavour
    -0.67
     eternity
    -0.67
     independ
    -0.66
     gobl
    -0.66
     colour
    -0.66
     unden
    -0.66
     enthusi
    -0.65
    POSITIVE LOGITS
     Additionally
    1.16
     Also
    1.12
     Similarly
    1.06
     Likewise
    1.02
     Critics
    0.95
     Similar
    0.94
     Previously
    0.94
     Those
    0.94
     Meanwhile
    0.93
     Both
    0.93
    Act Density 0.351%

    No Known Activations