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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "hook" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amer
    -0.16
     enlightenment
    -0.15
    odor
    -0.15
    iddet
    -0.15
    lee
    -0.14
    ammen
    -0.14
    encer
    -0.14
    åľ
    -0.14
    uously
    -0.14
    imdi
    -0.14
    POSITIVE LOGITS
     Hook
    0.20
    worm
    0.18
     Carousel
    0.17
    er
    0.17
    Hook
    0.17
    jaw
    0.17
    aroo
    0.16
    ered
    0.16
     hook
    0.16
    ups
    0.16
    Act Density 0.025%

    No Known Activations