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

    Neuronpedia

    INDEX
    Explanations

    references to "hammer" and its variations, indicating a focus on tools or actions associated with hammers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nap
    -0.16
    iband
    -0.15
    andler
    -0.15
     @$_
    -0.15
     Flyers
    -0.14
     Woodward
    -0.14
    çģ¯
    -0.14
    ãģĭãģĦ
    -0.14
    anna
    -0.14
    isse
    -0.14
    POSITIVE LOGITS
     hammer
    0.17
    storm
    0.17
    mith
    0.17
     sublic
    0.17
     dul
    0.17
    hammer
    0.16
    head
    0.16
    ing
    0.15
    ujete
    0.15
    \Base
    0.15
    Act Density 0.015%

    No Known Activations