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

    Neuronpedia

    INDEX
    Explanations

    verbs related to striking and attacking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Enti
    -0.48
    Libs
    -0.45
    melli
    -0.45
    øy
    -0.45
     Rani
    -0.43
     sàn
    -0.42
    getInteger
    -0.41
     Cosby
    -0.41
    li
    -0.40
    R
    -0.40
    POSITIVE LOGITS
     strikes
    1.45
     strike
    1.44
     Strikes
    1.42
    Strike
    1.37
     Strike
    1.36
     striking
    1.29
    strike
    1.29
     Striking
    1.28
     struck
    1.24
    struck
    1.04
    Act Density 0.055%

    No Known Activations