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

    Neuronpedia

    INDEX
    Explanations

    references to the word "hammer" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VICE
    -0.78
     Leone
    -0.77
    ITIES
    -0.75
    ITY
    -0.69
    RIP
    -0.67
    ected
    -0.67
     Charity
    -0.67
    ocard
    -0.66
    yon
    -0.65
    RIPT
    -0.65
    POSITIVE LOGITS
    sonian
    1.08
    bats
    0.96
     hammer
    0.95
    hammer
    0.93
    heads
    0.85
    head
    0.85
     hamm
    0.85
    lock
    0.82
     nails
    0.81
    ing
    0.81
    Act Density 0.004%

    No Known Activations