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

    Neuronpedia

    INDEX
    Explanations

    words related to hammers

    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
    ITIES
    -0.81
    RIP
    -0.80
    VICE
    -0.71
    redits
    -0.71
    cess
    -0.71
    uality
    -0.70
    ceed
    -0.70
    otes
    -0.68
    yon
    -0.68
    ITY
    -0.68
    POSITIVE LOGITS
     hammer
    1.01
    bats
    0.88
    sonian
    0.88
     hamm
    0.87
    heads
    0.87
     hammered
    0.87
    hammer
    0.84
     wrench
    0.79
    head
    0.79
     blow
    0.78
    Act Density 0.024%

    No Known Activations