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

    Neuronpedia

    INDEX
    Explanations

    references to various halls of fame and inductees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Animator
    -0.16
    ìĬ¹
    -0.16
    hiro
    -0.16
    инок
    -0.15
     prize
    -0.15
    odic
    -0.14
    icable
    -0.14
    otta
    -0.14
    odal
    -0.14
    ICC
    -0.14
    POSITIVE LOGITS
     Hall
    0.57
     induction
    0.54
     hall
    0.49
    Hall
    0.49
     indu
    0.45
    hall
    0.38
     Ind
    0.38
    ducted
    0.38
    duct
    0.37
     halls
    0.32
    Act Density 0.070%

    No Known Activations