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

    Neuronpedia

    INDEX
    Explanations

    technical terminology and references related to software and data packages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.68
    ↵
    -0.66
    .
    -0.64
    ↵↵
    -0.58
    ,
    -0.53
    ?
    -0.52
    -
    -0.52
    _
    -0.47
     I
    -0.47
    ruik
    -0.47
    POSITIVE LOGITS
     pleaſure
    1.09
     ſtate
    1.08
    ſelves
    1.06
     itſelf
    1.05
     Diſ
    1.03
     houſe
    1.03
    tagHelperRunner
    1.03
     myſelf
    1.01
     ſever
    1.01
     faſt
    0.99
    Act Density 0.514%

    No Known Activations