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

    Neuronpedia

    INDEX
    Explanations

    complex relationships and interactions between features and their predictive qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.25
     GenerationType
    -1.19
     itſelf
    -1.10
    AndEndTag
    -1.09
     Jefus
    -1.08
    ſelves
    -1.07
    bootstrapcdn
    -1.06
     fevere
    -1.03
    ^(@)
    -1.03
     whoſe
    -1.02
    POSITIVE LOGITS
    ,
    0.62
    .
    0.52
     .
    0.52
     (
    0.49
    ..
    0.48
    IT
    0.47
    s
    0.47
     or
    0.47
    **
    0.47
    ;
    0.46
    Act Density 0.914%

    No Known Activations