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

    Neuronpedia

    INDEX
    Explanations

    connectors and transition words that indicate relationships or sequences in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Marketable
    -0.16
    .AnchorStyles
    -0.15
     rumpe
    -0.15
    ãģ¾ãģ¾
    -0.15
    Dia
    -0.15
    zyst
    -0.15
    XHR
    -0.15
    eltas
    -0.14
    าà¸ĺ
    -0.14
     fetisch
    -0.14
    POSITIVE LOGITS
     La
    0.18
     Parallel
    0.18
     la
    0.18
    yth
    0.17
    Parallel
    0.17
     Something
    0.16
    y
    0.15
     El
    0.15
    alc
    0.15
     E
    0.15
    Act Density 0.015%

    No Known Activations