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

    Neuronpedia

    INDEX
    Explanations

    words related to time indicating a future event

    oai_token-act-pair · gpt-3.5-turbo

    references to imminent events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leck
    -0.75
    pat
    -0.74
    gem
    -0.72
    cipline
    -0.68
    arth
    -0.68
     Highest
    -0.65
    oret
    -0.64
    che
    -0.64
    icion
    -0.64
    yre
    -0.64
    POSITIVE LOGITS
     thereafter
    1.02
    aneously
    0.95
     soon
    0.94
    theless
    0.90
     afterward
    0.84
     afterwards
    0.83
     Soon
    0.80
    Soon
    0.75
     realised
    0.73
     puberty
    0.72
    Act Density 0.015%

    No Known Activations