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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases indicating plans or future actions related to career or positions

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

    Returned/pursued/offered, followed by an action

    np_acts-logits-general · gemini-2.0-flash

    verb followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     color
    -0.37
     hom
    -0.35
     commercial
    -0.33
     doctor
    -0.32
     Hom
    -0.32
    commercial
    -0.32
     mute
    -0.30
     tutti
    -0.30
     avant
    -0.30
    vom
    -0.30
    POSITIVE LOGITS
    rungsseite
    0.86
    verwijspagina
    0.59
    homonymie
    0.58
     autorytatywna
    0.57
    estacks
    0.52
    WriteTagHelper
    0.52
    Filmografia
    0.52
     fieldNum
    0.51
     nhàng
    0.51
    centralwidget
    0.50
    Act Density 0.396%

    No Known Activations