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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or contrasting statements

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

    Followed by conjunctions

    np_acts-logits-general · gemini-2.0-flash

    contrastors (but, however)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     it
    -0.52
     again
    -0.51
    Again
    -0.47
     although
    -0.46
     übrigens
    -0.46
     already
    -0.45
     further
    -0.43
     verder
    -0.43
     ferner
    -0.42
    stanti
    -0.42
    POSITIVE LOGITS
    今回
    1.03
    今回は
    1.00
    今回の
    0.93
    今回も
    0.90
     gynhyrchwyd
    0.86
    UserScript
    0.86
     تضيفلها
    0.82
     виправивши
    0.81
    這次
    0.80
    本次
    0.80
    Act Density 0.314%

    No Known Activations