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

    Neuronpedia

    INDEX
    Explanations

    programming commands and steps related to code execution and software development

    oai_token-act-pair · gpt-3.5-turbo

    technical instructions or steps related to software installation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     evidenced
    -0.79
     constit
    -0.77
     contested
    -0.75
     Samar
    -0.73
     spoiled
    -0.72
     fielded
    -0.72
     waged
    -0.71
     sanctioned
    -0.71
     harb
    -0.71
     belonged
    -0.70
    POSITIVE LOGITS
    Alternatively
    1.55
    Once
    1.48
    Step
    1.48
    Tip
    1.47
    Repeat
    1.47
    NOTE
    1.42
    Congratulations
    1.42
    Then
    1.42
    Finally
    1.40
    Next
    1.39
    Act Density 0.196%

    No Known Activations