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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technology and innovation

    oai_token-act-pair · gpt-3.5-turbo

    Text that contains various forms of a specific special character or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Aman
    -0.76
     Mysteries
    -0.72
     Stard
    -0.70
     ABE
    -0.70
     Jeanne
    -0.66
     guiActiveUnfocused
    -0.65
     Sieg
    -0.65
     Fighters
    -0.64
    eways
    -0.62
     Debor
    -0.62
    POSITIVE LOGITS
    ª
    1.02
    IJ
    0.90
    Ĵ
    0.89
    ¹
    0.87
    ittal
    0.87
    urion
    0.83
    ³
    0.82
    ł
    0.81
    possibly
    0.81
    «
    0.81
    Act Density 0.063%

    No Known Activations