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

    Neuronpedia

    INDEX
    Explanations

    verbs related to stopping or preventing actions

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to cessation or interruption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ighth
    -0.85
    oided
    -0.73
    ohl
    -0.70
    asus
    -0.69
    oru
    -0.65
    inals
    -0.65
    iquette
    -0.65
    axter
    -0.65
     Skydragon
    -0.63
     Printed
    -0.63
    POSITIVE LOGITS
     anymore
    1.00
     nor
    0.87
     until
    0.72
     anywhere
    0.66
     pursu
    0.65
     anybody
    0.64
     whatsoever
    0.62
    tered
    0.61
     laps
    0.61
     muster
    0.60
    Act Density 0.070%

    No Known Activations