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

    Neuronpedia

    INDEX
    Explanations

    phrases related to facts, evidence, and observations

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating relationships or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kees
    -0.87
    urs
    -0.82
    ummer
    -0.80
    itled
    -0.79
    ãĤº
    -0.78
    ãĤ¨ãĥ«
    -0.77
    achu
    -0.75
    iller
    -0.75
    itute
    -0.75
    ilk
    -0.74
    POSITIVE LOGITS
     supplemented
    0.98
     inexper
    0.98
     sheer
    0.97
     inertia
    0.95
     ingenuity
    0.94
     intuition
    0.92
     techniques
    0.87
     negligence
    0.87
     assumptions
    0.84
     familiarity
    0.81
    Act Density 0.411%

    No Known Activations