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

    Neuronpedia

    INDEX
    Explanations

    negations and their context in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    à¤Ĺर
    -0.15
    adj
    -0.14
    иÑĩеÑģки
    -0.14
    nox
    -0.14
    hell
    -0.14
    Dll
    -0.14
    hon
    -0.13
     gros
    -0.13
    overrides
    -0.13
     åī
    -0.13
    POSITIVE LOGITS
     gonna
    0.22
     necessarily
    0.20
     anymore
    0.19
     yet
    0.18
     rocket
    0.17
     going
    0.16
     even
    0.15
    ÏĦή
    0.15
     anywhere
    0.15
    vetica
    0.15
    Act Density 0.083%

    No Known Activations