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

    Neuronpedia

    INDEX
    Explanations

    phrases related to evaluating circumstances and making decisions

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

    Prepositions and conjunctions

    np_acts-logits-general · gemini-2.0-flash

    giving studentsgiving premiumgiving politiciansgiving mayorgiving enthusiastic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.90
     myſelf
    -0.89
     doubtnut
    -0.87
    ſelf
    -0.85
     itſelf
    -0.83
     iſt
    -0.83
     ་་
    -0.82
     Anſ
    -0.79
     ―――――
    -0.79
    ſelves
    -0.79
    POSITIVE LOGITS
     $\
    0.73
     a
    0.66
     Chwiliwch
    0.60
      
    0.56
     he
    0.56
     us
    0.56
     p
    0.54
     to
    0.54
     an
    0.53
     various
    0.53
    Act Density 0.230%

    No Known Activations