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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences expressing a lack of surprise

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a lack of surprise regarding various situations or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.92
    eatures
    -0.89
    abase
    -0.83
    senal
    -0.78
    İĭ
    -0.73
     eleph
    -0.71
    sembly
    -0.69
     exting
    -0.69
    ailability
    -0.68
     raft
    -0.67
    POSITIVE LOGITS
    imaru
    0.83
     anymore
    0.78
     whatsoever
    0.70
     nor
    0.70
     why
    0.65
    actionDate
    0.62
     Nunes
    0.61
    IELD
    0.61
    Nap
    0.60
    ा
    0.58
    Act Density 0.029%

    No Known Activations