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

    Neuronpedia

    INDEX
    Explanations

    phrases related to operations or functioning in different contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    grave
    -0.81
    hus
    -0.78
    plet
    -0.73
    ilde
    -0.69
     Shards
    -0.66
    alla
    -0.65
    urd
    -0.65
    hon
    -0.64
     Upton
    -0.64
    ingham
    -0.64
    POSITIVE LOGITS
     independently
    0.90
     concurrently
    0.83
     continuously
    0.80
     lawfully
    0.76
     illegally
    0.76
     jointly
    0.74
     smoothly
    0.73
    ATING
    0.73
    querade
    0.71
     autonom
    0.71
    Act Density 0.088%

    No Known Activations