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

    Neuronpedia

    INDEX
    Explanations

    phrases related to investigations or assessments of situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ISA
    -0.16
    ìģ
    -0.14
     завиÑģим
    -0.13
     DID
    -0.13
    ukt
    -0.13
    deps
    -0.13
    _UNUSED
    -0.13
    bury
    -0.13
     dealloc
    -0.13
    576
    -0.13
    POSITIVE LOGITS
     was
    0.51
    被
    0.45
     被
    0.42
    was
    0.40
     Äijược
    0.40
     zosta
    0.39
     бÑĭла
    0.38
     бÑĭл
    0.37
     were
    0.37
     been
    0.37
    Act Density 0.796%

    No Known Activations