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

    Neuronpedia

    INDEX
    Explanations

    phrases related to news headlines

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     citiz
    -0.77
     withdraw
    -0.75
     seiz
    -0.74
     deterrent
    -0.71
    ignty
    -0.70
     culmin
    -0.69
     retali
    -0.67
    EStream
    -0.67
     dissu
    -0.66
     withdrawal
    -0.65
    POSITIVE LOGITS
    Seriously
    0.92
    Ear
    0.78
    WB
    0.78
    Sure
    0.76
    hello
    0.73
    Fans
    0.72
    Specifically
    0.72
    7601
    0.70
    Think
    0.69
    Houston
    0.69
    Act Density 0.249%

    No Known Activations