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

    Neuronpedia

    INDEX
    Explanations

    verbs related to forming or creating something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "form" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reys
    -0.80
    rey
    -0.70
    ILLE
    -0.68
    yssey
    -0.67
    Rare
    -0.63
    ily
    -0.60
    bley
    -0.59
     offend
    -0.57
    yes
    -0.56
    ysis
    -0.56
    POSITIVE LOGITS
    aldehyde
    1.27
    ulates
    1.22
    idable
    1.19
    ulating
    1.15
    ulas
    1.09
    atter
    1.03
    ulate
    0.98
    ulators
    0.96
    furt
    0.90
    ative
    0.90
    Act Density 0.018%

    No Known Activations