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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to qualities or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to productivity and progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortium
    -0.76
     Cosponsors
    -0.64
    emonium
    -0.63
     Historic
    -0.62
     Preferred
    -0.61
    endum
    -0.60
    ospons
    -0.59
     GOODMAN
    -0.59
    osponsors
    -0.58
    vernment
    -0.57
    POSITIVE LOGITS
     diarrhea
    0.58
     Diesel
    0.53
     thirst
    0.53
     sickness
    0.52
     tasted
    0.51
     edges
    0.51
     flares
    0.50
     outwe
    0.50
     Rebell
    0.50
    entimes
    0.50
    Act Density 1.811%

    No Known Activations