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

    Neuronpedia

    INDEX
    Explanations

    phrases related to mysteries, secrets, or hidden information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.75
     Manhattan
    -0.74
     scattering
    -0.74
     scatter
    -0.73
     collect
    -0.68
     exhib
    -0.65
     collecting
    -0.64
     Send
    -0.64
     shack
    -0.64
     dispers
    -0.62
    POSITIVE LOGITS
    ¬
    1.46
    ľ
    1.33
    º
    1.24
    ı
    1.20
    Ĵ
    1.18
    ¡
    1.17
    Ķ
    1.16
    ¹
    1.16
    ¼
    1.14
    į
    1.14
    Act Density 0.964%

    No Known Activations