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

    Neuronpedia

    INDEX
    Explanations

    verbs related to stopping or halting

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "stop" and its variations in a variety of contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eers
    -0.70
    fortune
    -0.68
    dor
    -0.68
    ALD
    -0.67
    ally
    -0.66
    eur
    -0.65
    dds
    -0.65
    eer
    -0.64
    ERS
    -0.63
    ever
    -0.62
    POSITIVE LOGITS
     short
    1.01
    gap
    0.98
     abruptly
    0.97
     bothering
    0.91
     midway
    0.90
     breathing
    0.89
     halfway
    0.83
     altogether
    0.82
     momentarily
    0.82
     responding
    0.75
    Act Density 0.061%

    No Known Activations