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

    Neuronpedia

    INDEX
    Explanations

    expressions that indicate varying degrees of complexity, significance, or knowledge in different contexts

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

    fairly/somewhat degree modifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stadio
    -0.42
    絶対に
    -0.39
    ientí
    -0.38
     tjen
    -0.38
     asla
    -0.38
    たびに
    -0.37
    /*
    -0.37
     telefónica
    -0.37
     absolutely
    -0.37
     kuş
    -0.36
    POSITIVE LOGITS
     bastante
    0.66
     fairly
    0.62
     Somewhat
    0.61
    somewhat
    0.60
     довольно
    0.60
    (?)
    0.59
    Somewhat
    0.59
    ParallelGroup
    0.55
     (?)
    0.55
    tagHelperRunner
    0.55
    Act Density 0.191%

    No Known Activations