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

    Neuronpedia

    INDEX
    Explanations

    phrases related to plans, actions, or intentions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating possession or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    advertising
    -0.77
    die
    -0.72
    inventoryQuantity
    -0.68
    ThumbnailImage
    -0.67
    ava
    -0.67
    ģĸ
    -0.66
    pire
    -0.66
    athon
    -0.64
    Usage
    -0.64
    soever
    -0.64
    POSITIVE LOGITS
     chance
    0.90
     opportunity
    0.90
     glimpse
    0.82
     obligation
    0.76
     wonderful
    0.72
     abundance
    0.72
     idea
    0.71
     glimps
    0.70
     knack
    0.68
     choice
    0.67
    Act Density 0.274%

    No Known Activations