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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or unexpected outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     незавершена
    -0.74
    gameserver
    -0.59
    ſelf
    -0.59
     disambiguazione
    -0.58
     mxArray
    -0.57
    ☚
    -0.56
    posedge
    -0.56
    Sklici
    -0.54
    NameInMap
    -0.53
    AndEndTag
    -0.53
    POSITIVE LOGITS
     surprisingly
    1.96
     Surprisingly
    1.56
    Surprisingly
    1.50
     oddly
    1.30
     strangely
    1.26
     surprising
    1.25
     unexpectedly
    1.23
     weirdly
    1.20
     interestingly
    1.20
     remarkably
    1.16
    Act Density 0.170%

    No Known Activations