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

    Neuronpedia

    INDEX
    Explanations

    phrases related to education or academic programs

    oai_token-act-pair · gpt-3.5-turbo

    indicators of events or instances related to time or timelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hovah
    -0.95
    ,,,,
    -0.86
    å§
    -0.77
    aucas
    -0.70
     Filipino
    -0.69
    ewitness
    -0.69
    indu
    -0.69
    humane
    -0.68
     !!
    -0.67
    rican
    -0.66
    POSITIVE LOGITS
     caveats
    0.88
     Slate
    0.86
     Emacs
    0.72
     tweaks
    0.71
     sket
    0.70
     refinement
    0.68
     narrower
    0.68
     Centauri
    0.68
     Machina
    0.67
     nifty
    0.66
    Act Density 1.706%

    No Known Activations