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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sudden impacts or realizations

    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
    umption
    -0.75
    ilon
    -0.74
    ORY
    -0.70
    enser
    -0.68
    entric
    -0.68
    iliary
    -0.67
    ensor
    -0.66
    itive
    -0.66
    adian
    -0.65
    pora
    -0.65
    POSITIVE LOGITS
     struck
    0.93
     striking
    0.87
    achi
    0.82
     mast
    0.70
     resemb
    0.69
    tered
    0.68
     strike
    0.66
     audible
    0.66
    ãĤ¤ãĥĪ
    0.66
     Burnett
    0.64
    Act Density 0.013%

    No Known Activations