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

    Neuronpedia

    INDEX
    Explanations

    additions or statements made by someone

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating contributions or statements made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kat
    -0.67
    luaj
    -0.66
    Enlarge
    -0.65
    ardless
    -0.64
    ograms
    -0.64
    bird
    -0.63
    é¾įåĸļ士
    -0.62
    toggle
    -0.62
    fare
    -0.62
    ogram
    -0.60
    POSITIVE LOGITS
    ictions
    1.05
     insult
    0.84
     omin
    0.84
    itious
    0.83
    missions
    0.82
    itionally
    0.81
    itions
    0.81
    icted
    0.79
     inval
    0.76
    iction
    0.75
    Act Density 0.031%

    No Known Activations