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

    Neuronpedia

    INDEX
    Explanations

    instances of personal pronouns and assessments of individual experiences

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

    Followed by "but" or "also"

    np_acts-logits-general · gemini-2.0-flash

    pronoun and followed by a contrasting conjunction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     therefore
    -0.95
     zwar
    -0.91
     sice
    -0.89
    therefore
    -0.85
     even
    -0.81
     hence
    -0.78
     infatti
    -0.78
    thus
    -0.77
    จึง
    -0.76
     thus
    -0.74
    POSITIVE LOGITS
     nonetheless
    1.14
     ändå
    1.13
     nevertheless
    1.12
    却
    1.10
    卻
    1.09
    却是
    1.05
     lại
    1.01
     digress
    0.99
    却被
    0.97
     trotzdem
    0.95
    Act Density 0.667%

    No Known Activations