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

    Neuronpedia

    INDEX
    Explanations

    phrases related to observation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "see" with various contexts of agreement or positivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bee
    -0.72
    iera
    -0.71
    alone
    -0.68
     proble
    -0.67
    uez
    -0.65
    ÃŃa
    -0.65
    é¾
    -0.64
    orage
    -0.64
    ieri
    -0.63
    fur
    -0.63
    POSITIVE LOGITS
    enance
    0.87
     someone
    0.71
     him
    0.67
     them
    0.67
     parallels
    0.66
     somebody
    0.66
     PSU
    0.66
     how
    0.65
    terson
    0.65
    dogs
    0.63
    Act Density 0.070%

    No Known Activations