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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing beliefs or opinions

    oai_token-act-pair · gpt-3.5-turbo

    assertions of belief or conviction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cloth
    -0.71
    aste
    -0.71
    details
    -0.66
     Household
    -0.64
    ham
    -0.62
     Navigation
    -0.62
     Pavilion
    -0.61
    effect
    -0.61
    abb
    -0.61
    Appearance
    -0.61
    POSITIVE LOGITS
     passionately
    0.82
    ħ
    0.78
    §
    0.75
    phas
    0.73
     compelled
    0.70
    POSE
    0.70
     believe
    0.69
    fully
    0.68
    ieve
    0.67
    rica
    0.67
    Act Density 0.044%

    No Known Activations