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

    Neuronpedia

    INDEX
    Explanations

    quoted strings and their formatting details in code or data schemas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.35
    ſelves
    -1.30
     فريبيس
    -1.25
    )";
    -1.25
    .")
    -1.23
    ."</
    -1.22
     itſelf
    -1.20
     $_"
    -1.19
     myſelf
    -1.19
    ſelf
    -1.18
    POSITIVE LOGITS
     "
    0.86
     “
    0.86
    :
    0.79
    ="
    0.75
    =
    0.74
     (
    0.72
     =
    0.70
     :
    0.67
     '
    0.63
     
    0.63
    Act Density 0.168%

    No Known Activations