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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of fire

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "arm"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vide
    -0.72
     RTX
    -0.65
     porous
    -0.64
    KEY
    -0.61
     Sound
    -0.59
     procedural
    -0.58
     Plat
    -0.58
     Chou
    -0.58
     wo
    -0.58
     particular
    -0.57
    POSITIVE LOGITS
    ageddon
    1.31
    arm
    1.19
    ament
    1.11
    arms
    1.03
    aments
    0.99
    esan
    0.96
    chair
    0.95
    achine
    0.94
    obil
    0.90
    stadt
    0.90
    Act Density 0.006%

    No Known Activations