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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or subjective opinions about experiences

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

    "sounds" followed by an adjective

    np_acts-logits-general · gemini-2.0-flash

    sounds like adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gynhyrchwyd
    -0.60
     consistently
    -0.48
    hyrchwyd
    -0.48
    '])->
    -0.47
    ))=\
    -0.47
    >'+
    -0.47
    يكب
    -0.46
     comunque
    -0.46
    DockStyle
    -0.45
    timewa
    -0.45
    POSITIVE LOGITS
     sounds
    1.60
     Sounds
    1.42
     sounding
    1.33
    Sounds
    1.32
    sounds
    1.30
     SOUND
    1.27
     sound
    1.22
     klingt
    1.20
     sounded
    1.17
     Sound
    1.09
    Act Density 0.167%

    No Known Activations