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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notations related to equations and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ‚
    -0.72
     }?>
    -0.59
     breech
    -0.59
     Económica
    -0.58
     maer
    -0.56
     pleaſure
    -0.53
     oignons
    -0.52
     }).
    -0.52
     greateſt
    -0.52
     workman
    -0.52
    POSITIVE LOGITS
     \
    0.91
     \%
    0.64
    (\
    0.63
    ^{\
    0.60
    _{
    0.59
     \$
    0.58
    -\
    0.56
    ždý
    0.56
     \&
    0.56
     \#
    0.54
    Act Density 0.859%

    No Known Activations