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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditions, functionalities, and qualities of objects or concepts in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Beijinhos
    -0.64
    Atentamente
    -0.63
     Efq
    -0.61
     rodríguez
    -0.60
     Jefus
    -0.59
    FormTagHelper
    -0.58
    miyorum
    -0.58
     Houſe
    -0.58
    –¿
    -0.58
    ValueStyle
    -0.58
    POSITIVE LOGITS
    它
    0.92
     its
    0.91
    它的
    0.85
    Its
    0.83
     Its
    0.82
     它
    0.79
     it
    0.74
    它是
    0.70
     It
    0.68
     itself
    0.66
    Act Density 0.847%

    No Known Activations