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

    Neuronpedia

    INDEX
    Explanations

    adjectives that describe the impact or quality of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "make" and its variations indicating causation or creation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thia
    -0.74
    ban
    -0.63
    phrine
    -0.62
     nurs
    -0.62
     champ
    -0.62
     scrimmage
    -0.61
     presided
    -0.59
     vest
    -0.58
     reigning
    -0.56
     bour
    -0.56
    POSITIVE LOGITS
    hift
    1.10
     sure
    0.97
     sense
    0.90
     headlines
    0.83
    enders
    0.81
    ender
    0.78
     Sense
    0.76
     landfall
    0.74
    akable
    0.73
    itives
    0.73
    Act Density 0.127%

    No Known Activations