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

    Neuronpedia

    INDEX
    Explanations

    expressions of knowledge, awareness, or understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cubit
    -0.81
    Datuak
    -0.76
    MockBean
    -0.74
    ngdoc
    -0.71
     ligiloj
    -0.67
     unknownFields
    -0.66
     estekak
    -0.66
     eventdata
    -0.65
     pageContext
    -0.64
    ьа
    -0.63
    POSITIVE LOGITS
     Never
    0.62
    Never
    0.62
    never
    0.61
    NEVER
    0.55
     never
    0.53
     jamás
    0.52
     jamais
    0.49
    Instance
    0.49
     Always
    0.48
     nigdy
    0.47
    Act Density 0.115%

    No Known Activations