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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "kind" to indicate types or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Дереккөздер
    -1.08
    cifix
    -0.95
     Roach
    -0.92
    ectomy
    -0.88
     educativas
    -0.87
    décoration
    -0.87
     nicio
    -0.86
     Rossa
    -0.85
     Geller
    -0.84
     Matos
    -0.84
    POSITIVE LOGITS
     Kind
    1.33
     KIND
    1.28
    kind
    1.25
    Kind
    1.20
    KIND
    1.19
     kind
    1.16
    Kinds
    1.13
    kinds
    1.04
     Kinds
    0.96
     kinds
    0.94
    Act Density 0.044%

    No Known Activations