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

    Neuronpedia

    INDEX
    Explanations

    sentences related to decision-making and opinions

    oai_token-act-pair · gpt-3.5-turbo

    statements expressing certainty or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.88
     perpetrators
    -0.71
     assailants
    -0.67
    negie
    -0.66
     Shutterstock
    -0.65
     robber
    -0.65
    vict
    -0.63
    代
    -0.63
     impoverished
    -0.62
     è£ıç
    -0.60
    POSITIVE LOGITS
    initely
    1.18
    laughs
    1.03
     definitely
    1.00
    ecided
    1.00
     TBA
    0.95
    absolutely
    0.91
     gonna
    0.91
     yeah
    0.89
     definite
    0.88
     speculation
    0.86
    Act Density 0.364%

    No Known Activations