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

    Neuronpedia

    INDEX
    Explanations

    terms related to errors or invalid entries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    addContainerGap
    -0.64
    TimerTask
    -0.59
    Ikus
    -0.59
     rayures
    -0.58
     prochaines
    -0.57
    циони
    -0.57
     bellas
    -0.56
     communiquez
    -0.53
    tre
    -0.53
    ЩЕ
    -0.53
    POSITIVE LOGITS
     inverse
    1.00
    inv
    0.97
    inverse
    0.95
     Inverse
    0.90
     invas
    0.90
    Inverse
    0.87
     INV
    0.87
    INV
    0.85
     intim
    0.83
     inv
    0.82
    Act Density 0.102%

    No Known Activations