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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the involvement or inclusion of something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "part"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    borg
    -0.71
    ometers
    -0.70
    ovich
    -0.68
    ield
    -0.66
    burg
    -0.60
    mong
    -0.58
    resh
    -0.58
     Cooldown
    -0.57
    Alert
    -0.55
    hots
    -0.54
    POSITIVE LOGITS
     part
    3.53
     parts
    2.03
    part
    1.99
    Part
    1.85
     portion
    1.83
     Part
    1.75
    parts
    1.53
     PART
    1.46
     Parts
    1.40
     portions
    1.36
    Act Density 0.050%

    No Known Activations