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

    Neuronpedia

    INDEX
    Explanations

    quantifiers indicating amounts or quantities

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

    do with some

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ***!
    -0.33
     garrafa
    -0.33
    browserify
    -0.32
     młod
    -0.30
    obacter
    -0.30
    ii
    -0.29
    i
    -0.29
    guar
    -0.29
     malam
    -0.28
     keber
    -0.28
    POSITIVE LOGITS
    Doing
    0.77
    doing
    0.77
     Doing
    0.76
     doing
    0.75
     done
    0.71
     Done
    0.69
     doin
    0.65
     DOING
    0.65
    Done
    0.63
     Audiodateien
    0.61
    Act Density 0.026%

    No Known Activations