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

    Neuronpedia

    INDEX
    Explanations

    words expressing uncertainty or likelihood

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

    sometimes, possibly, perhaps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+
    -0.50
    antMatchers
    -0.45
     motocic
    -0.43
    SupportActionBar
    -0.42
    RTCK
    -0.40
     propOrder
    -0.40
     useDispatch
    -0.39
    toggler
    -0.39
    ViewImports
    -0.39
    PasswordEncoder
    -0.38
    POSITIVE LOGITS
     often
    0.56
     linkovi
    0.56
     taking
    0.53
     usually
    0.51
    évaluateur
    0.49
     never
    0.48
     without
    0.47
     gärna
    0.47
    ("")]
    0.46
     quietly
    0.45
    Act Density 0.055%

    No Known Activations