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

    Neuronpedia

    INDEX
    Explanations

    references to specific training programs or systems in a structured context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    žel
    -0.20
    :convert
    -0.15
     histograms
    -0.14
    ovah
    -0.14
    flen
    -0.14
     Param
    -0.14
     BaseEntity
    -0.13
    863
    -0.13
    stry
    -0.13
    ">&#
    -0.13
    POSITIVE LOGITS
    azzi
    0.18
    oub
    0.16
    jan
    0.15
     anth
    0.15
    (ST
    0.14
    loud
    0.14
    ellite
    0.14
    elli
    0.14
    inite
    0.14
    roz
    0.14
    Act Density 0.022%

    No Known Activations