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

    Neuronpedia

    INDEX
    Explanations

    key terms and phrases that denote inquiry or confirmation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .synthetic
    -0.18
    ãĥĥãĥģ
    -0.16
    asin
    -0.16
     εμÏĢ
    -0.15
    ango
    -0.15
    angen
    -0.15
    ButtonType
    -0.15
    óst
    -0.15
    podob
    -0.14
    aravel
    -0.14
    POSITIVE LOGITS
    agar
    0.18
    essenger
    0.17
    im
    0.15
     agar
    0.15
    est
    0.15
    estre
    0.15
    iets
    0.14
    itom
    0.14
     Mount
    0.14
    428
    0.14
    Act Density 0.001%

    No Known Activations