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

    Neuronpedia

    INDEX
    Explanations

    phrases related to reduction or decrease

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to reduction or minimizing various factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mire
    -0.76
    ADRA
    -0.70
    wine
    -0.68
    lished
    -0.64
    eret
    -0.61
    hol
    -0.61
    cue
    -0.61
    POL
    -0.61
    £ı
    -0.61
     Ãī
    -0.60
    POSITIVE LOGITS
     incidence
    1.02
     effectiveness
    0.97
     burden
    0.95
     amount
    0.94
     unwanted
    0.91
     footprint
    0.90
     liability
    0.89
     reliance
    0.88
     inhib
    0.87
     intensity
    0.86
    Act Density 0.121%

    No Known Activations