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

    Neuronpedia

    INDEX
    Explanations

    references to voting and ratings in the context of products or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     behavi
    -0.80
    NESS
    -0.78
     tremend
    -0.71
     simultane
    -0.68
    matter
    -0.67
     neigh
    -0.67
    reality
    -0.64
    nos
    -0.64
     reality
    -0.62
    ulence
    -0.62
    POSITIVE LOGITS
    abled
    1.20
    arthed
    1.20
    pleted
    1.18
    ased
    1.15
    lished
    1.14
    ached
    1.08
    tained
    1.07
    aired
    1.07
    anked
    1.04
    aded
    1.04
    Act Density 0.098%

    No Known Activations