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

    Neuronpedia

    INDEX
    Explanations

    elements related to attributes and behaviors in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amt
    -0.16
    OTE
    -0.16
    ade
    -0.16
    illard
    -0.14
    CADE
    -0.14
    oub
    -0.14
    edor
    -0.14
    vyk
    -0.14
    ROUGH
    -0.13
    åħ
    -0.13
    POSITIVE LOGITS
     unlike
    0.91
     Unlike
    0.65
    Unlike
    0.64
     whereas
    0.52
     compared
    0.51
     Whereas
    0.47
     contrary
    0.41
     Compared
    0.39
     contrast
    0.35
    contrast
    0.33
    Act Density 0.589%

    No Known Activations