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

    Neuronpedia

    INDEX
    Explanations

    phrases highlighting various issues or problems

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the existence or presence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascript
    -0.81
    Enlarge
    -0.71
    én
    -0.68
    Explore
    -0.66
    Contents
    -0.65
    Materials
    -0.65
     aims
    -0.63
    chairs
    -0.62
    entials
    -0.62
    #$#$
    -0.62
    POSITIVE LOGITS
     the
    0.67
     looming
    0.64
     Leban
    0.63
     another
    0.61
     Starship
    0.61
     Babel
    0.60
     Boo
    0.60
     Birch
    0.60
     Judith
    0.59
     Stuff
    0.59
    Act Density 0.134%

    No Known Activations