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

    Neuronpedia

    INDEX
    Explanations

    the word "to"

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing uncertainty or questioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĿ
    -0.77
    bley
    -0.65
    letter
    -0.64
     McCann
    -0.64
     Nurs
    -0.63
     Corpus
    -0.63
    cycle
    -0.62
    HP
    -0.62
    SEE
    -0.62
    ©¶æ¥µ
    -0.61
    POSITIVE LOGITS
     why
    0.85
    yx
    0.81
    ggles
    0.78
     date
    0.78
     whether
    0.77
    wered
    0.76
     ascertain
    0.73
    ingu
    0.72
     blame
    0.70
    ipal
    0.67
    Act Density 0.029%

    No Known Activations