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

    Neuronpedia

    INDEX
    Explanations

    the word "no."

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

    Follows "no" and indicates a change

    np_acts-logits-general · gemini-2.0-flash

    no longer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CanadaChoose
    -0.73
    Hochspringen
    -0.73
    ScopeManager
    -0.72
    kloped
    -0.68
     متعلقه
    -0.65
    Zeneca
    -0.64
    AutoScale
    -0.63
    bootstrapcdn
    -0.63
     المعيارى
    -0.63
    Życiorys
    -0.63
    POSITIVE LOGITS
     longer
    0.73
     worse
    0.67
     lenger
    0.63
     less
    0.59
    TimerTask
    0.56
     better
    0.55
    worse
    0.54
     more
    0.53
    longer
    0.52
     længere
    0.51
    Act Density 0.055%

    No Known Activations