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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "unusually" along with the following content in the text

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that describe the degree of unusualness or extremity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rum
    -0.73
    haven
    -0.72
    uese
    -0.70
    lord
    -0.70
    icular
    -0.69
    ocol
    -0.69
     Destination
    -0.69
    ipal
    -0.67
    icipated
    -0.67
     Cities
    -0.67
    POSITIVE LOGITS
     blinding
    0.76
     unstable
    0.74
     LIMITED
    0.72
     impressed
    0.70
     proficient
    0.70
     unusually
    0.70
     chilly
    0.69
     blinded
    0.68
     enthusi
    0.68
    dylib
    0.68
    Act Density 0.016%

    No Known Activations