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

    Neuronpedia

    INDEX
    Explanations

    phrases related to fictional characters or books

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate significance or describe notable events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nces
    -0.75
     FY
    -0.68
    hement
    -0.67
    hots
    -0.64
    ioned
    -0.64
    Ĭ
    -0.64
    aph
    -0.63
    osaurus
    -0.62
     veto
    -0.62
     BT
    -0.61
    POSITIVE LOGITS
    Enlarge
    0.99
    Actor
    0.81
    Years
    0.80
    Adapt
    0.78
    toggle
    0.78
    anooga
    0.78
    Neal
    0.75
    MIT
    0.74
    nin
    0.73
    Written
    0.71
    Act Density 0.057%

    No Known Activations