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

    Neuronpedia

    INDEX
    Explanations

    sentences that indicate a problem or issue needing attention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personendaten
    -1.39
    AnimationsModule
    -1.21
    :✨
    -1.16
    SharedCtor
    -1.14
    principalColumn
    -1.12
     nakalista
    -1.12
     EconPapers
    -1.10
    parsedMessage
    -1.07
    NameInMap
    -1.04
     Signalez
    -1.03
    POSITIVE LOGITS
    .
    0.67
    The
    0.59
    ,
    0.51
    my
    0.47
     The
    0.47
    ↵
    0.46
     my
    0.46
    ↵↵
    0.45
    I
    0.42
     
    0.41
    Act Density 0.606%

    No Known Activations