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

    Neuronpedia

    INDEX
    Explanations

    phrases related to caring about people, issues, or specific groups

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate concern or interest in people and their needs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ross
    -0.84
    cession
    -0.81
    BuyableInstoreAndOnline
    -0.81
    hesis
    -0.78
    Figure
    -0.77
    atar
    -0.75
    igmatic
    -0.75
    Lay
    -0.74
    hiba
    -0.73
    Cola
    -0.71
    POSITIVE LOGITS
     preserving
    0.95
     respecting
    0.84
    lessly
    0.84
     fairness
    0.80
     protecting
    0.78
     aesthetics
    0.77
     integrity
    0.77
     politics
    0.75
     preservation
    0.75
     maximizing
    0.75
    Act Density 0.032%

    No Known Activations