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

    Neuronpedia

    INDEX
    Explanations

    references to giant-sized entities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "giant" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the descriptor 'giant'

    oai_token-act-pair · gpt-4-turbo
    New Auto-Interp
    Negative Logits
    iggins
    -0.82
    yrinth
    -0.81
    iring
    -0.81
    schild
    -0.77
     Cunning
    -0.76
    pai
    -0.76
    oral
    -0.75
    lest
    -0.75
    iency
    -0.75
    blance
    -0.73
    POSITIVE LOGITS
     squid
    0.94
     elephant
    0.84
     gorilla
    0.83
     strides
    0.80
     leap
    0.79
     penis
    0.77
    gest
    0.77
     aster
    0.77
     chunk
    0.76
     leaps
    0.76
    Act Density 0.017%

    No Known Activations