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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize comparison or relativity with the majority

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or patterns indicating a sense of commonality or generalization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rematch
    -0.69
     Cosponsors
    -0.68
     disposed
    -0.63
    gee
    -0.62
    dayName
    -0.61
     bowling
    -0.60
    ĸļ
    -0.60
    acus
    -0.60
     Quote
    -0.58
     depot
    -0.57
    POSITIVE LOGITS
    course
    0.79
    ãĤ¢ãĥ«
    0.75
    THING
    0.74
     course
    0.70
    requisites
    0.67
    flight
    0.67
    ãĥĩãĤ£
    0.67
    ocated
    0.65
    Downloadha
    0.65
     us
    0.64
    Act Density 0.101%

    No Known Activations