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

    Neuronpedia

    INDEX
    Explanations

    words related to hammers and physical force

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "hammer" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ected
    -0.74
    cius
    -0.71
    uality
    -0.68
    eca
    -0.66
    otes
    -0.66
    æĥ
    -0.66
    ribune
    -0.65
    DragonMagazine
    -0.64
    RIP
    -0.63
    uce
    -0.62
    POSITIVE LOGITS
    hammer
    1.06
    sonian
    1.06
    heads
    1.04
    head
    1.03
    stone
    0.91
    bats
    0.89
    ing
    0.87
    ding
    0.86
     hammer
    0.85
    mort
    0.80
    Act Density 0.053%

    No Known Activations