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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to physical attributes and states

    oai_token-act-pair · gpt-3.5-turbo

    vocabulary related to various conditions, characteristics, and qualities of individuals or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ju
    -0.72
    PN
    -0.70
    alyst
    -0.68
    Nar
    -0.65
    oji
    -0.65
    Adv
    -0.63
    sterdam
    -0.63
    ainer
    -0.63
    Stream
    -0.61
    Bomb
    -0.61
    POSITIVE LOGITS
    tarian
    0.83
    isable
    0.76
     (<
    0.72
     setups
    0.70
     Swed
    0.67
     constructs
    0.66
    iberal
    0.65
    ened
    0.65
     shack
    0.63
     tabl
    0.62
    Act Density 0.305%

    No Known Activations