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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical elements like software development or coding

    oai_token-act-pair · gpt-3.5-turbo

    special characters and symbols used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sapphire
    -0.67
     scattering
    -0.65
     shack
    -0.65
     infringing
    -0.65
     Thy
    -0.64
     Samson
    -0.64
     Manhattan
    -0.64
     Sapp
    -0.63
    anwhile
    -0.62
     Samar
    -0.62
    POSITIVE LOGITS
    ¬
    1.49
    ¡
    1.31
    į
    1.31
    ĺ
    1.25
    ²
    1.24
    ¹
    1.23
    ľ
    1.23
    ı
    1.21
    Ĵ
    1.21
    º
    1.18
    Act Density 0.237%

    No Known Activations