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

    Neuronpedia

    INDEX
    Explanations

    programming code syntax and command structures

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly those used to enclose or terminate statements and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oria
    -0.74
    rament
    -0.68
    rum
    -0.68
    estation
    -0.68
    ku
    -0.67
    =-=-=-=-=-=-=-=-
    -0.67
     Dull
    -0.66
    matically
    -0.64
    µ
    -0.63
    nam
    -0.62
    POSITIVE LOGITS
    arthed
    0.79
    ONSORED
    0.76
    ategory
    0.74
     srfAttach
    0.73
    theless
    0.73
    oldemort
    0.72
    aucuses
    0.72
    ascade
    0.71
    ricanes
    0.70
    uador
    0.69
    Act Density 0.023%

    No Known Activations