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

    Neuronpedia

    INDEX
    Explanations

    negative expressions of uncertainty or lack of knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.89
    Personendaten
    -0.83
    RenderAtEndOf
    -0.81
    WithIOException
    -0.78
     lenker
    -0.73
    twimg
    -0.72
     calendriers
    -0.71
    ">—
    -0.71
     vPvB
    -0.70
    riwal
    -0.70
    POSITIVE LOGITS
     know
    0.97
    know
    0.69
     how
    0.67
     why
    0.66
     knows
    0.64
     believe
    0.64
     understand
    0.63
    Know
    0.61
     Know
    0.60
     whether
    0.59
    Act Density 0.147%

    No Known Activations