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

    Neuronpedia

    INDEX
    Explanations

    mentions of giant-sized objects or creatures

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "giant."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yrinth
    -0.83
    qi
    -0.75
    issance
    -0.74
    actionDate
    -0.71
    earch
    -0.71
    ople
    -0.70
    iggins
    -0.70
    earcher
    -0.70
    ntax
    -0.70
    erate
    -0.69
    POSITIVE LOGITS
     squid
    1.01
     leap
    0.84
     leaps
    0.84
     bould
    0.84
     gorilla
    0.78
     Squid
    0.77
     chunks
    0.77
     chunk
    0.77
     sized
    0.77
     scale
    0.76
    Act Density 0.029%

    No Known Activations