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

    Neuronpedia

    INDEX
    Explanations

    specific markers or indicators related to document structure or formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.68
    ly
    -0.61
    ième
    -0.61
    yty
    -0.61
    pylab
    -0.61
    Getenv
    -0.60
    memberOf
    -0.59
     memer
    -0.59
    PathVariable
    -0.58
    argout
    -0.58
    POSITIVE LOGITS
    enterOuterAlt
    0.80
    ￡
    0.76
    ukone
    0.73
    tigungs
    0.71
     
    0.70
     CreateTagHelper
    0.70
     Pv
    0.69
    thest
    0.69
    \{\\
    0.68
    stums
    0.68
    Act Density 0.613%

    No Known Activations