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

    Neuronpedia

    INDEX
    Explanations

    phrases related to encouragement and motivation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of excitement or enthusiasm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arte
    -0.77
     implied
    -0.73
     msec
    -0.66
    ividual
    -0.64
     historically
    -0.64
     unmarked
    -0.64
    xtap
    -0.64
    ufact
    -0.63
    ittal
    -0.63
    ectomy
    -0.62
    POSITIVE LOGITS
    Laughs
    0.77
    --------------------------------------------------------
    0.75
    Ü
    0.72
    ONSORED
    0.72
    !!!
    0.72
    !!!!
    0.69
    YES
    0.69
    agan
    0.67
    !!
    0.66
    laughs
    0.65
    Act Density 0.247%

    No Known Activations