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

    Neuronpedia

    INDEX
    Explanations

    scientific terminologies related to physical phenomena and their mathematical representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    findpost
    -0.65
    原始内容存档于
    -0.54
     authorised
    -0.51
    addHandler
    -0.51
    alagi
    -0.48
    munic
    -0.48
     autorisé
    -0.47
     individuale
    -0.47
     NgModule
    -0.47
     authorized
    -0.46
    POSITIVE LOGITS
     reversed
    1.87
     swap
    1.86
     reversal
    1.80
     swapped
    1.76
     Swap
    1.71
     swapping
    1.67
     reversing
    1.66
     reverse
    1.65
     flipped
    1.61
     reverses
    1.59
    Act Density 0.465%

    No Known Activations