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

    Neuronpedia

    INDEX
    Explanations

    code snippets and functions related to string handling and whitespace management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orthand
    -0.16
    urum
    -0.15
    ynes
    -0.15
    -dot
    -0.14
     lowercase
    -0.14
     Above
    -0.14
    solete
    -0.14
    ector
    -0.14
    efon
    -0.14
     perman
    -0.13
    POSITIVE LOGITS
     spaces
    0.50
     space
    0.46
     Spaces
    0.41
    Spaces
    0.39
     SPACE
    0.39
    SPACE
    0.39
    -space
    0.39
     Space
    0.39
    space
    0.38
    spaces
    0.38
    Act Density 0.091%

    No Known Activations