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

    Neuronpedia

    INDEX
    Explanations

    references to individuals' desires and aspirations

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

    Followed by "used"

    np_acts-logits-general · gemini-2.0-flash

    used to, are, can, will

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     is
    -0.54
    twimg
    -0.54
     Ha
    -0.51
     a
    -0.47
     (
    -0.46
     Home
    -0.46
    Referencie
    -0.45
     Gil
    -0.44
     “
    -0.44
    Odkazy
    -0.43
    POSITIVE LOGITS
     ddelweddau
    0.86
     crdi
    0.80
    Datuak
    0.77
     Pergamon
    0.76
     cdti
    0.76
    StoryboardSegue
    0.76
    AxisAlignment
    0.73
    ConstraintMaker
    0.71
     tfsi
    0.70
    ὖ
    0.70
    Act Density 0.227%

    No Known Activations