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

    Neuronpedia

    INDEX
    Explanations

    words related to decisions and choices

    oai_token-act-pair · gpt-3.5-turbo

    terms related to significant decisions and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancies
    -0.82
    onyms
    -0.70
    utenberg
    -0.68
    dimension
    -0.66
    undreds
    -0.65
    verning
    -0.65
     contracting
    -0.64
    iries
    -0.63
     roofs
    -0.63
    reys
    -0.61
    POSITIVE LOGITS
     nonetheless
    1.03
     considering
    1.03
     indeed
    1.02
     compared
    0.90
     opener
    0.71
    Reviewer
    0.71
     huh
    0.68
    capt
    0.66
    undrum
    0.66
     nevertheless
    0.65
    Act Density 0.269%

    No Known Activations