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

    Neuronpedia

    INDEX
    Explanations

    keywords or special characters in a specific layout

    oai_token-act-pair · gpt-3.5-turbo

    special character sequences or symbols often used in digital communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uded
    -0.71
    ieth
    -0.70
    izen
    -0.67
    ayed
    -0.64
     appropriated
    -0.64
    sighted
    -0.64
     dorm
    -0.63
    itatively
    -0.62
     guided
    -0.62
    NetMessage
    -0.62
    POSITIVE LOGITS
    Ģ
    1.22
    ðŁĺ
    1.22
    ī
    1.07
    ©
    1.06
    Ľ
    1.03
    ³
    1.03
    Ħ
    1.01
    ¦
    1.01
    į
    1.00
    Ĩ
    0.98
    Act Density 0.006%

    No Known Activations