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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate absence or lack of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the absence of serious incidents or injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rex
    -0.80
    otton
    -0.73
    rn
    -0.71
    minus
    -0.70
    often
    -0.70
    gat
    -0.70
    gypt
    -0.69
    mire
    -0.69
    FML
    -0.68
    dit
    -0.68
    POSITIVE LOGITS
     indication
    1.25
     indications
    1.15
     definitive
    1.00
     formal
    1.00
     surprises
    0.98
     longer
    0.95
     additional
    0.95
     conclusive
    0.94
     immediate
    0.94
     arrests
    0.92
    Act Density 0.110%

    No Known Activations