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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific aims or targets

    oai_token-act-pair · gpt-3.5-turbo

    sentences that indicate intent or purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.76
    士
    -0.75
    lv
    -0.69
    Import
    -0.69
    Column
    -0.68
    Closure
    -0.68
     Solitaire
    -0.68
    alter
    -0.67
    meta
    -0.67
    story
    -0.66
    POSITIVE LOGITS
     aimed
    1.09
     aiming
    0.97
     toward
    0.87
     squarely
    0.83
    sonian
    0.82
     targeting
    0.81
     towards
    0.80
     provoking
    0.79
    ovie
    0.79
    emouth
    0.78
    Act Density 0.012%

    No Known Activations