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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence of additional information or depth in a given context

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating potential or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andestine
    -0.69
    washer
    -0.68
    chy
    -0.65
    soever
    -0.63
    inel
    -0.62
    ety
    -0.62
    hip
    -0.61
    estial
    -0.61
    arity
    -0.61
    ashes
    -0.60
    POSITIVE LOGITS
     learn
    0.97
     be
    0.97
     explore
    0.92
     discuss
    0.88
     consider
    0.87
     come
    0.87
     discover
    0.87
     accomplish
    0.83
     worry
    0.83
     contend
    0.80
    Act Density 0.071%

    No Known Activations