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

    Neuronpedia

    INDEX
    Explanations

    the word "unlike" to draw comparisons or contrasts between subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stag
    -0.17
    istique
    -0.16
    tec
    -0.16
    erton
    -0.15
    Commerce
    -0.15
    irth
    -0.15
    ú
    -0.14
    nage
    -0.14
    thane
    -0.14
    manship
    -0.13
    POSITIVE LOGITS
     unlike
    0.19
     previous
    0.15
    TabPage
    0.15
    654
    0.15
    upe
    0.14
    ably
    0.14
    ollah
    0.14
    usual
    0.14
     Unlike
    0.14
    ItemSelected
    0.14
    Act Density 0.014%

    No Known Activations