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

    Neuronpedia

    INDEX
    Explanations

    emoticons and symbols, particularly arrows (âĢ)

    oai_token-act-pair · gpt-3.5-turbo

    recurring symbols or unusual characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     recogn
    -0.67
     scatter
    -0.65
    anwhile
    -0.65
    ortium
    -0.62
     Amon
    -0.62
     Mov
    -0.62
     scattering
    -0.61
     simul
    -0.60
     Jem
    -0.59
     scattered
    -0.59
    POSITIVE LOGITS
    ľ
    1.47
    ¬
    1.46
    ¡
    1.43
    ¦
    1.37
    ĸ
    1.33
    ł
    1.25
    Ł
    1.25
    Ĵ
    1.23
    ķ
    1.22
    ĵ
    1.22
    Act Density 0.166%

    No Known Activations