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

    Neuronpedia

    INDEX
    Explanations

    words ending in "-wards"

    oai_token-act-pair · gpt-3.5-turbo

    words related to awards and recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cited
    -0.70
     artifact
    -0.58
     Rafael
    -0.56
     Monitor
    -0.56
     obstruction
    -0.54
     Ari
    -0.54
     used
    -0.54
     quoted
    -0.54
    ody
    -0.53
     Corp
    -0.53
    POSITIVE LOGITS
    wards
    4.99
    ward
    2.40
    WARD
    1.79
    stairs
    1.08
     forwards
    1.03
     downwards
    1.01
     backwards
    1.01
    chieve
    1.00
    dates
    0.99
    monds
    0.96
    Act Density 0.011%

    No Known Activations