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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making an argument or point

    oai_token-act-pair · gpt-3.5-turbo

    statements or phrases related to beliefs and opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    araoh
    -0.64
    youtube
    -0.62
     unsuspecting
    -0.62
    FOX
    -0.61
    Hundreds
    -0.60
    someone
    -0.60
    Thank
    -0.60
    Thousands
    -0.58
    iuses
    -0.58
    SPONSORED
    -0.58
    POSITIVE LOGITS
     differentiation
    0.86
     specificity
    0.79
     heterogeneity
    0.79
     consistency
    0.75
     differences
    0.75
     breadth
    0.73
     continuity
    0.73
     emphasis
    0.72
     attrition
    0.71
     durability
    0.71
    Act Density 0.913%

    No Known Activations