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

    Neuronpedia

    INDEX
    Explanations

    negative statements indicating uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or lack of clarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.69
     horizont
    -0.65
    tes
    -0.64
    livion
    -0.63
    iasis
    -0.61
    letter
    -0.61
    Tes
    -0.61
    ience
    -0.60
    standing
    -0.58
     Reloaded
    -0.57
    POSITIVE LOGITS
     disclosed
    1.12
     yet
    1.04
     divul
    0.98
     immediately
    0.98
     discl
    0.95
     disclose
    0.92
     clear
    0.92
     specified
    0.88
     authorized
    0.86
     known
    0.85
    Act Density 0.091%

    No Known Activations