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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or lack of understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "I don't" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    don't know, don't think, don't see

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.93
    onAttach
    -0.82
    rrggbb
    -0.78
    -0.76
    Personendaten
    -0.75
     NSCoder
    -0.72
     calendriers
    -0.71
    DockStyle
    -0.71
    LabelTagHelper
    -0.70
    tagHelperRunner
    -0.70
    POSITIVE LOGITS
     know
    0.88
     why
    0.72
     blame
    0.72
     how
    0.68
     understand
    0.66
     sure
    0.64
     think
    0.63
     believe
    0.60
     care
    0.56
     see
    0.56
    Act Density 0.132%

    No Known Activations