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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate comparisons or contrasts, particularly in a competitive context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.91
     utafitiHapana
    -0.64
     Fryer
    -0.61
    uxxxx
    -0.58
     pegat
    -0.56
     चीज़ों
    -0.56
     ProtoMessage
    -0.56
     Memo
    -0.55
    Portail
    -0.54
    msgTypes
    -0.54
    POSITIVE LOGITS
     GenerationType
    0.64
    tector
    0.57
    GEBURTSDATUM
    0.56
    ：“……”
    0.55
    PARATUS
    0.53
    selbe
    0.52
     bezoek
    0.50
    鰭
    0.49
    入って
    0.48
     semplicemente
    0.47
    Act Density 0.210%

    No Known Activations