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

    Neuronpedia

    INDEX
    Explanations

    the word "Long" and "short", particularly when referring to "Long Beach" and "short film."

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with 'long'

    np_token-act-pair-logits · gpt-4o-mini

    Long

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DrawerToggle
    -0.53
     lòng
    -0.51
    dafri
    -0.47
    ocino
    -0.47
    UpInside
    -0.47
     kuiten
    -0.46
     rocas
    -0.46
     mukaan
    -0.46
     fondateur
    -0.46
    enterOuterAlt
    -0.46
    POSITIVE LOGITS
    ueil
    0.63
     gone
    0.57
     BoxDecoration
    0.56
     дописавши
    0.55
    oria
    0.54
    MLLoader
    0.54
    ώρα
    0.52
    ="@+
    0.52
    AutoField
    0.51
    ue
    0.51
    Act Density 0.269%

    No Known Activations