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

    Neuronpedia

    INDEX
    Explanations

    references to specific entities or categories, particularly related to approvals or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kit
    -0.15
    inz
    -0.15
    istor
    -0.14
     Frankfurt
    -0.14
     Middle
    -0.14
    ORIZONTAL
    -0.14
     Kurt
    -0.14
     Heck
    -0.14
    ÙĬÙĩ
    -0.13
    ones
    -0.13
    POSITIVE LOGITS
    sett
    0.17
    leo
    0.15
    âĨĴâĨĴ
    0.15
    quito
    0.15
    aley
    0.15
    ahlen
    0.14
    ë§ī
    0.14
    Ñħи
    0.14
     кип
    0.14
    FINE
    0.14
    Act Density 0.005%

    No Known Activations