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

    Neuronpedia

    INDEX
    Explanations

    instances where someone is expressing an opinion or statement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "say" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gart
    -0.86
    Mech
    -0.70
    equipped
    -0.70
    plete
    -0.69
    hardt
    -0.68
    endor
    -0.65
    xtap
    -0.65
     Entered
    -0.64
    mentation
    -0.64
    stru
    -0.64
    POSITIVE LOGITS
     goodbye
    0.92
     aloud
    0.76
     loudly
    0.74
     about
    0.72
    terday
    0.67
     afterwards
    0.66
     Sask
    0.65
     Mulcair
    0.65
     Chomsky
    0.65
    INGS
    0.65
    Act Density 0.055%

    No Known Activations