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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technology and popular culture

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a structured or formatted list

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     intervals
    -0.76
     interval
    -0.74
     cir
    -0.70
     rink
    -0.69
     square
    -0.69
     exha
    -0.67
     parachute
    -0.67
     MEN
    -0.67
     sacrific
    -0.66
     bowel
    -0.66
    POSITIVE LOGITS
    style
    1.95
    esque
    1.94
    inspired
    1.89
    themed
    1.84
    like
    1.79
    related
    1.72
    type
    1.65
    sized
    1.63
    derived
    1.62
    based
    1.61
    Act Density 0.104%

    No Known Activations