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

    Neuronpedia

    INDEX
    Explanations

    variables and code snippets, including assigning values and functions

    oai_token-act-pair · gpt-3.5-turbo

    elements related to programming syntax and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oppos
    -0.73
    pmwiki
    -0.71
    arily
    -0.57
     ACTIONS
    -0.57
    taboola
    -0.56
     adversaries
    -0.55
     incumb
    -0.54
     conflic
    -0.54
    allel
    -0.54
    judicial
    -0.53
    POSITIVE LOGITS
    Shell
    0.62
     KL
    0.57
     Pass
    0.55
     McKay
    0.54
     Shell
    0.54
     Channel
    0.54
    example
    0.53
     Label
    0.53
     Example
    0.52
    Jr
    0.51
    Act Density 1.222%

    No Known Activations