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

    Neuronpedia

    INDEX
    Explanations

    actions or intentions related to future plans or changes in a project

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    emonic
    -0.64
    achine
    -0.62
     Creator
    -0.61
    76561
    -0.61
     Unknown
    -0.60
     constit
    -0.58
    osi
    -0.57
     supposedly
    -0.57
     Soph
    -0.57
    Numbers
    -0.57
    POSITIVE LOGITS
     tomorrow
    0.81
     gladly
    0.80
     phased
    0.79
    fall
    0.75
     soon
    0.74
    fitting
    0.74
     rewarded
    0.73
     forever
    0.72
     sorely
    0.71
     able
    0.69
    Act Density 1.712%

    No Known Activations