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

    Neuronpedia

    INDEX
    Explanations

    expressions of remorse and requests for forgiveness

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

    Expressions of apology and regret

    np_acts-logits-general · gemini-2.0-flash

    apologizing and remorse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     onlook
    -0.53
     iVar
    -0.53
     jealous
    -0.52
     "','
    -0.52
     envy
    -0.51
    Datuak
    -0.51
     riv
    -0.51
     mola
    -0.51
     empowerment
    -0.50
    chenkt
    -0.50
    POSITIVE LOGITS
     apologized
    1.10
     apology
    1.08
     remorse
    1.05
     apologizing
    1.03
     apologize
    0.98
     apologised
    0.94
     apologies
    0.89
     apologe
    0.83
     apologise
    0.83
     apolog
    0.78
    Act Density 0.328%

    No Known Activations