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

    Neuronpedia

    INDEX
    Explanations

    phrases related to upcoming events or releases

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating upcoming events or releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    claimer
    -0.67
    ruff
    -0.64
     Parables
    -0.64
    oller
    -0.61
    isma
    -0.61
    ds
    -0.61
    olkien
    -0.61
    ording
    -0.60
    archives
    -0.60
    ÃŃa
    -0.60
    POSITIVE LOGITS
    Soon
    1.09
     undone
    1.01
     Soon
    0.99
     soon
    0.92
     attractions
    0.90
    soon
    0.85
     apart
    0.81
     together
    0.77
     closer
    0.76
     up
    0.76
    Act Density 0.048%

    No Known Activations