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

    Neuronpedia

    INDEX
    Explanations

    references to statistical or experimental factors and their influences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mktime
    -0.14
    ignum
    -0.13
    ayload
    -0.13
     Arist
    -0.12
    ARB
    -0.12
    ENDOR
    -0.12
    ÙĥÙħ
    -0.12
     mathematic
    -0.12
    á»ķ
    -0.12
    عÙĪد
    -0.12
    POSITIVE LOGITS
     experiments
    0.28
     Experiment
    0.27
     experiment
    0.25
    Experiment
    0.24
     trained
    0.22
     abl
    0.22
    å®ŀéªĮ
    0.22
     experimented
    0.21
    experiment
    0.21
     train
    0.21
    Act Density 0.046%

    No Known Activations