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

    Neuronpedia

    INDEX
    Explanations

    references to the name "Arthur."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     uſe
    -0.64
     ſche
    -0.64
     Rump
    -0.63
     MPR
    -0.63
     Safer
    -0.61
     estekak
    -0.61
    Cue
    -0.61
    warn
    -0.61
     Optimum
    -0.61
     ſever
    -0.60
    POSITIVE LOGITS
     createSlice
    0.70
    ագրություններ
    0.69
    Naissance
    0.66
    pulumi
    0.62
     così
    0.58
    Ghz
    0.56
    ...@
    0.56
    колеп
    0.55
    saraba
    0.54
    Grüsse
    0.54
    Act Density 0.101%

    No Known Activations