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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making or causing something to happen

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    yd
    -0.67
     consulted
    -0.66
    bow
    -0.61
    Ha
    -0.60
    ban
    -0.58
    \-
    -0.58
    ologue
    -0.56
     signed
    -0.56
     modeled
    -0.56
     tweeted
    -0.56
    POSITIVE LOGITS
     us
    1.01
     him
    0.80
     them
    0.77
     me
    0.76
     tremend
    0.76
    SPONSORED
    0.73
     viewers
    0.71
    olves
    0.71
     havoc
    0.70
     investors
    0.70
    Act Density 1.416%

    No Known Activations