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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating past occurrences and references to existence or presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.51
    transQ
    -0.48
     CreateTagHelper
    -0.48
    ContextHolder
    -0.46
    tagHelperRunner
    -0.44
    windowFixed
    -0.42
     Including
    -0.40
     którzy
    -0.40
     которые
    -0.40
    stateProvider
    -0.40
    POSITIVE LOGITS
     comprised
    1.07
     composed
    0.96
     based
    0.87
     actually
    0.86
     considered
    0.79
     located
    0.75
     merely
    0.74
     characterized
    0.72
     represented
    0.72
     caused
    0.72
    Act Density 1.353%

    No Known Activations