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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant announcements or actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    usha
    -0.70
     Participation
    -0.69
     Flavoring
    -0.64
    ontent
    -0.62
     Dur
    -0.61
    mates
    -0.60
    endon
    -0.60
    erved
    -0.59
     Surprise
    -0.59
    rates
    -0.58
    POSITIVE LOGITS
     anecd
    0.84
     anyways
    0.81
     anyway
    0.80
     thing
    0.79
    ryu
    0.74
     legally
    0.73
     cheaply
    0.72
     unilaterally
    0.71
     differently
    0.71
    wrong
    0.71
    Act Density 0.042%

    No Known Activations