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

    Neuronpedia

    INDEX
    Explanations

    examples of various things among others

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate additional information or examples related to a topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ister
    -0.70
    ukong
    -0.69
     NRL
    -0.69
    iker
    -0.69
     Patent
    -0.67
    ocene
    -0.64
     Donkey
    -0.64
     Belfast
    -0.64
    ISTER
    -0.63
    ories
    -0.62
    POSITIVE LOGITS
    worldly
    0.93
     considerations
    0.93
     factors
    0.92
     reasons
    0.90
     things
    0.90
     feats
    0.84
     places
    0.79
    types
    0.79
    tions
    0.79
    urances
    0.77
    Act Density 0.032%

    No Known Activations