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

    Neuronpedia

    INDEX
    Explanations

    technical text containing symbols like 'âĢ'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the symbol combination 'âĢ' in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scattering
    -0.79
     fart
    -0.72
     swept
    -0.72
     Tanz
    -0.71
     tremend
    -0.67
     Sapp
    -0.67
     strap
    -0.65
     Spit
    -0.64
     blond
    -0.64
     Glou
    -0.63
    POSITIVE LOGITS
    ¬
    1.14
    £
    1.13
    ¡
    1.11
    Ĵ
    1.10
    ı
    1.09
    ¹
    1.03
    ħ
    1.01
    ¤
    1.00
    ®
    0.98
    Mech
    0.98
    Act Density 0.202%

    No Known Activations