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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence or absence of something

    oai_token-act-pair · gpt-3.5-turbo

    assertions or discussions about the existence or non-existence of entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    step
    -0.70
    bill
    -0.68
    ajo
    -0.67
    med
    -0.66
    jug
    -0.65
    Thom
    -0.64
    anche
    -0.63
     broom
    -0.62
    mar
    -0.62
    Dro
    -0.61
    POSITIVE LOGITS
    nces
    0.91
    entials
    0.81
    entially
    0.78
    rences
    0.73
     existed
    0.72
    lihood
    0.68
    ality
    0.67
    places
    0.67
     exists
    0.66
     predic
    0.65
    Act Density 0.034%

    No Known Activations