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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences related to removing or getting rid of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with eliminating or removing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.65
    ANS
    -0.63
    mpeg
    -0.60
    Leaks
    -0.59
     Maced
    -0.59
    operation
    -0.59
     Jonah
    -0.59
     McDonnell
    -0.58
    CAN
    -0.58
    Recommend
    -0.57
    POSITIVE LOGITS
    anium
    0.90
    icide
    0.81
    icides
    0.81
    eness
    0.80
    ged
    0.80
    uations
    0.76
    ings
    0.76
    ients
    0.75
    urga
    0.75
    estone
    0.75
    Act Density 0.030%

    No Known Activations