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

    Neuronpedia

    INDEX
    Explanations

    phrases related to causality and importance

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating causation or explanation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     clipboard
    -0.67
    ahs
    -0.67
     sheets
    -0.64
    keys
    -0.63
    sheets
    -0.61
     slips
    -0.61
    abytes
    -0.60
     freezes
    -0.60
    bats
    -0.57
    umbs
    -0.57
    POSITIVE LOGITS
     Fuller
    0.65
    ^^^^
    0.63
    manuel
    0.62
     misunder
    0.61
    JUST
    0.61
    raq
    0.61
     Santos
    0.61
     Firstly
    0.61
     striking
    0.60
     borne
    0.59
    Act Density 0.878%

    No Known Activations