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

    Neuronpedia

    INDEX
    Explanations

    conditional and contrasting statements

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

    following conditional conjunctions

    np_acts-logits-general · gemini-2.0-flash

    contrasting or qualifying conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wenigstens
    -0.52
    VALID
    -0.47
     F
    -0.46
     good
    -0.46
     immerhin
    -0.44
     valid
    -0.43
     W
    -0.43
    pyplot
    -0.42
     sal
    -0.42
     useful
    -0.42
    POSITIVE LOGITS
    хьтан
    0.81
     myſelf
    0.81
    ollectionView
    0.79
     ſmall
    0.78
     Slight
    0.77
    uxxxx
    0.76
     skep
    0.76
     slightly
    0.76
    GEBURTSDATUM
    0.75
    slightly
    0.75
    Act Density 0.330%

    No Known Activations