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

    Neuronpedia

    INDEX
    Explanations

    mentions of timing in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to timing in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ousy
    -0.80
    inis
    -0.76
    vasive
    -0.75
    thus
    -0.74
    rd
    -0.72
    haps
    -0.67
    tained
    -0.67
     Flavoring
    -0.67
    nered
    -0.67
    joining
    -0.66
    POSITIVE LOGITS
     timing
    1.20
     reversal
    0.81
     shenan
    0.81
     delays
    0.80
     sequencing
    0.77
     timed
    0.75
     delay
    0.75
    pring
    0.75
     revers
    0.75
     synchron
    0.73
    Act Density 0.007%

    No Known Activations