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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing size or scale

    oai_token-act-pair · gpt-3.5-turbo

    empty tokens or placeholders in text, indicating segments where content might be inserted or described

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ARB
    -0.82
    METHOD
    -0.77
    ancers
    -0.76
    gemony
    -0.76
    anship
    -0.76
    anwhile
    -0.75
    Sex
    -0.74
    Theme
    -0.73
    utics
    -0.72
    CF
    -0.71
    POSITIVE LOGITS
     chunk
    1.18
     sized
    1.13
     wooden
    1.12
     rectangular
    1.10
     intestine
    1.03
     hole
    1.03
     boulder
    1.03
     rectangle
    1.02
     pile
    1.02
     diameter
    1.01
    Act Density 0.127%

    No Known Activations