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

    Neuronpedia

    INDEX
    Explanations

    phrases related to scattered or spread objects or items

    oai_token-act-pair · gpt-3.5-turbo

    references to fragmented or scattered elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rament
    -0.71
    inem
    -0.68
    encing
    -0.68
    ral
    -0.67
    alty
    -0.65
    ird
    -0.64
    versible
    -0.63
    imir
    -0.63
    itability
    -0.63
     booster
    -0.63
    POSITIVE LOGITS
     havoc
    0.84
    Ùħ
    0.75
    ت
    0.72
     certs
    0.69
     piles
    0.68
    FACE
    0.65
    YING
    0.65
     Flavoring
    0.64
    adoes
    0.64
    ktop
    0.64
    Act Density 0.105%

    No Known Activations