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

    Neuronpedia

    INDEX
    Explanations

    terms and structures related to mathematical proofs and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     =
    -2.06
    =
    -2.04
     $=
    -1.66
     $=$
    -1.57
    ='
    -1.56
    ={
    -1.56
    =\
    -1.54
    =$
    -1.53
    =-
    -1.52
    ="
    -1.50
    POSITIVE LOGITS
    Aholisi
    0.44
    $​
    0.42
    Vidite
    0.41
    ,’’
    0.40
     perman
    0.39
    wartet
    0.38
     handles
    0.38
    atiche
    0.38
    ecia
    0.38
    ziehungs
    0.38
    Act Density 2.236%

    No Known Activations