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

    Neuronpedia

    INDEX
    Explanations

    phrases related to impacts or significant events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "struck" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iliary
    -0.79
    ORY
    -0.76
    umption
    -0.74
    ŀ
    -0.70
    omore
    -0.70
    enser
    -0.69
    Growing
    -0.69
    cler
    -0.67
    ilon
    -0.67
    adian
    -0.67
    POSITIVE LOGITS
     resemb
    0.84
     striking
    0.79
     struck
    0.74
    breakers
    0.72
     strike
    0.72
    ters
    0.71
    tered
    0.70
    achi
    0.70
     resemblance
    0.69
     mast
    0.66
    Act Density 0.025%

    No Known Activations