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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time and deadlines

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the progress or timeline of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sqor
    -0.71
     To
    -0.59
     forgetting
    -0.58
    Downloadha
    -0.58
     POLITICO
    -0.56
     Ender
    -0.56
     tiss
    -0.54
     peas
    -0.53
    uador
    -0.53
    acca
    -0.51
    POSITIVE LOGITS
    VIDIA
    0.75
    IRE
    0.67
    luence
    0.64
    igious
    0.62
    ÙIJ
    0.62
    dule
    0.61
    Alert
    0.60
    ISE
    0.60
    inion
    0.59
    uke
    0.59
    Act Density 0.290%

    No Known Activations