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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time or a temporary situation

    oai_token-act-pair · gpt-3.5-turbo

    future-oriented phrases indicating uncertainty or waiting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atars
    -0.71
    igham
    -0.67
     guiActiveUn
    -0.66
    obook
    -0.66
    osponsors
    -0.61
    abul
    -0.60
    ventus
    -0.60
     Reborn
    -0.59
    esar
    -0.59
    acious
    -0.59
    POSITIVE LOGITS
     suffice
    0.88
     remain
    0.80
     quo
    0.78
     stays
    0.73
     stay
    0.72
     continue
    0.72
     remains
    0.71
     impunity
    0.67
     stagn
    0.67
     concentrate
    0.66
    Act Density 0.241%

    No Known Activations