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

    Neuronpedia

    INDEX
    Explanations

    phrases related to future events or plans

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    nor
    -0.63
     unatt
    -0.63
    lust
    -0.61
    owered
    -0.58
     constituted
    -0.58
     stem
    -0.56
     predatory
    -0.55
    quartered
    -0.54
     purportedly
    -0.54
    orbit
    -0.54
    POSITIVE LOGITS
     ya
    1.06
     soon
    0.95
    later
    0.91
    essee
    0.89
     tomorrow
    0.86
     thee
    0.86
     someday
    0.85
     shortly
    0.84
    eeee
    0.83
     later
    0.79
    Act Density 0.161%

    No Known Activations