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

    Neuronpedia

    INDEX
    Explanations

    phrases related to rejection or refusal

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to decisions or proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Travels
    -0.74
    ukong
    -0.74
     Refuge
    -0.66
     Transparency
    -0.61
     Transgender
    -0.60
     Poverty
    -0.60
    ructose
    -0.59
    urches
    -0.59
     Highlights
    -0.59
     SHARES
    -0.57
    POSITIVE LOGITS
     nonetheless
    1.20
     nevertheless
    0.98
    etheless
    0.78
     thereto
    0.73
     retained
    0.71
     afterward
    0.69
    ).[
    0.67
     afterwards
    0.67
     suffice
    0.67
     thereafter
    0.65
    Act Density 1.335%

    No Known Activations