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

    Neuronpedia

    INDEX
    Explanations

    words related to items or concepts that can be modified or adjusted

    oai_token-act-pair · gpt-3.5-turbo

    words related to capabilities and functions of items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tug
    -0.72
     struggle
    -0.63
     trem
    -0.61
     stroke
    -0.60
     finger
    -0.57
     shove
    -0.54
     riff
    -0.54
     Prest
    -0.54
     lens
    -0.53
     fist
    -0.53
    POSITIVE LOGITS
    ables
    4.81
    able
    2.60
    ABLE
    2.43
    abled
    2.03
    ability
    1.96
    abling
    1.83
    ably
    1.83
    abilities
    1.68
    ibles
    1.48
    abl
    1.40
    Act Density 0.010%

    No Known Activations