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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "size" is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    sections of text that contain a description of a large creature, particularly within fictional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bara
    -0.84
    rique
    -0.84
    arie
    -0.75
    ILLE
    -0.75
    rov
    -0.71
    ibur
    -0.70
    veyard
    -0.70
    issance
    -0.69
    rea
    -0.68
    âķIJâķIJ
    -0.68
    POSITIVE LOGITS
     scale
    0.94
     stature
    0.90
     discrepancy
    0.79
     difference
    0.79
     proportion
    0.77
     footprint
    0.77
     mismatch
    0.75
     scales
    0.74
     proportions
    0.74
     size
    0.72
    Act Density 0.049%

    No Known Activations