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

    Neuronpedia

    INDEX
    Explanations

    verbs related to communication or expression

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    xtap
    -0.79
    folios
    -0.77
    estern
    -0.73
    ritional
    -0.71
    pleting
    -0.71
    mental
    -0.69
    folio
    -0.65
    agos
    -0.63
    gotten
    -0.63
    ockets
    -0.63
    POSITIVE LOGITS
     goodbye
    1.76
     hello
    1.31
     aloud
    1.24
     farewell
    1.09
     Goodbye
    1.05
     bye
    1.02
     loudly
    1.01
     hi
    0.96
     sorry
    0.88
     nothing
    0.84
    Act Density 0.673%

    No Known Activations