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

    Neuronpedia

    INDEX
    Explanations

    specific identifiers or attributes in a structured data format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     himſelf
    -1.16
     itſelf
    -1.13
     themſelves
    -1.05
     myſelf
    -1.04
     Efq
    -1.04
     iſt
    -1.02
     ſche
    -0.97
     Reſ
    -0.95
     purpoſe
    -0.95
     Houſe
    -0.94
    POSITIVE LOGITS
    sen
    0.54
    en
    0.54
     
    0.51
    mo
    0.50
     Om
    0.48
    му
    0.47
     Gor
    0.47
    Om
    0.47
     /
    0.47
    de
    0.47
    Act Density 0.033%

    No Known Activations