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

    Neuronpedia

    INDEX
    Explanations

    specific time formats

    oai_token-act-pair · gpt-3.5-turbo

    sequences of numbers and timestamps related to events or schedules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.72
    quez
    -0.71
    abilities
    -0.71
    ally
    -0.69
    obal
    -0.68
    osaurus
    -0.67
    alis
    -0.65
    oat
    -0.64
    alities
    -0.64
    loo
    -0.64
    POSITIVE LOGITS
    /#
    0.74
    ISTER
    0.74
    --+
    0.74
     hrs
    0.74
    arters
    0.73
    rpm
    0.72
    ##
    0.70
    âĤ¬
    0.69
    º
    0.68
     GHz
    0.68
    Act Density 0.023%

    No Known Activations