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

    Neuronpedia

    INDEX
    Explanations

    phrases related to action cessation or prevention

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express the concept of stopping or ceasing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ighth
    -0.91
    ortment
    -0.71
    gow
    -0.69
    hler
    -0.69
    jay
    -0.69
    ternity
    -0.69
    yssey
    -0.68
    sonian
    -0.68
    than
    -0.67
    per
    -0.67
    POSITIVE LOGITS
     anymore
    1.01
     nor
    0.97
     pursu
    0.80
     anybody
    0.76
     anyone
    0.67
     temptation
    0.64
     dragging
    0.63
     anything
    0.63
     pace
    0.61
     until
    0.59
    Act Density 0.104%

    No Known Activations