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

    Neuronpedia

    INDEX
    Explanations

    expressions of honesty and frankness

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

    honestly expressing doubt or opinion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nemlig
    -0.60
    FunctionFlags
    -0.59
     surla
    -0.56
     namelijk
    -0.55
     appunto
    -0.53
    たしか
    -0.51
    pium
    -0.51
    cass
    -0.50
     Signalez
    -0.49
    確かに
    -0.49
    POSITIVE LOGITS
     felt
    0.47
     feels
    0.47
     agak
    0.45
     probably
    0.44
     could
    0.44
     honesty
    0.43
     couldn
    0.42
     sorprender
    0.41
     prefier
    0.41
     honestly
    0.41
    Act Density 0.005%

    No Known Activations