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

    Neuronpedia

    INDEX
    Explanations

    terms related to special interests or special provisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "special" followed by other words

    np_acts-logits-general · gemini-2.0-flash

    "special" followed by specific type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -0.60
     mouseY
    -0.59
    tanleria
    -0.59
    queryInterface
    -0.58
     незавершена
    -0.55
    CopyWith
    -0.51
    kå
    -0.50
    fattning
    -0.49
    }>;
    -0.49
    batis
    -0.48
    POSITIVE LOGITS
     special
    0.96
    SPECIAL
    0.90
     Special
    0.89
     SPECIAL
    0.82
    Special
    0.82
     speciale
    0.82
    special
    0.81
    Sonder
    0.81
     spéciaux
    0.76
     purpose
    0.75
    Act Density 0.060%

    No Known Activations