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

    Neuronpedia

    INDEX
    Explanations

    specific phrases or combinations of letters and words that likely indicate special formatting or programming functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.09
     himſelf
    -1.02
     itſelf
    -1.00
     houſe
    -0.99
     poffible
    -0.95
     themſelves
    -0.91
     Jefus
    -0.90
     Efq
    -0.89
     theſe
    -0.87
     faſt
    -0.87
    POSITIVE LOGITS
    tagHelper
    0.55
     Te
    0.48
    ​
    0.46
     ​
    0.46
     te
    0.44
    redhat
    0.43
     Pri
    0.43
    Tē
    0.42
     Fe
    0.42
    Te
    0.42
    Act Density 0.221%

    No Known Activations