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

    Neuronpedia

    INDEX
    Explanations

    phrases related to increasing or enhancement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "increase."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aries
    -0.70
     Healer
    -0.68
    mates
    -0.67
    puted
    -0.66
    ··
    -0.66
     Monstrous
    -0.65
     ¯
    -0.65
    gets
    -0.63
    ician
    -0.63
    bane
    -0.62
    POSITIVE LOGITS
     exponentially
    0.99
    xual
    0.92
     subsequ
    0.86
     awareness
    0.84
    imar
    0.83
     materially
    0.83
    ornia
    0.82
     sidx
    0.80
     enormously
    0.78
     arousal
    0.76
    Act Density 0.044%

    No Known Activations