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

    Neuronpedia

    INDEX
    Explanations

    phrases related to events or actions being described by a third party

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "according to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eleph
    -0.75
     exting
    -0.75
    ailability
    -0.70
    Þ
    -0.66
    ccording
    -0.65
     occas
    -0.62
    uckland
    -0.61
     helicop
    -0.60
     conflic
    -0.56
    otor
    -0.56
    POSITIVE LOGITS
     to
    1.03
     TO
    0.76
     thereto
    0.71
    to
    0.66
     Reuters
    0.62
     POLITICO
    0.61
     sources
    0.60
     To
    0.58
    To
    0.55
    %]
    0.51
    Act Density 0.050%

    No Known Activations