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

    Neuronpedia

    INDEX
    Explanations

    statements that include the word "not" in conjunction with verbs or adjectives

    oai_token-act-pair · gpt-3.5-turbo

    assertions or definitive statements regarding conditions or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Occupations
    -0.64
     Rape
    -0.63
    OB
    -0.63
    arine
    -0.63
    $$$$
    -0.62
    WT
    -0.61
    kay
    -0.61
    Dest
    -0.61
    hart
    -0.60
    Cook
    -0.60
    POSITIVE LOGITS
     nonetheless
    1.55
     nevertheless
    1.33
    etheless
    1.04
     still
    0.86
     strangely
    0.85
     proble
    0.80
     adamant
    0.78
     persisted
    0.77
     thereto
    0.77
     retained
    0.76
    Act Density 1.004%

    No Known Activations