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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating negation or denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    üb
    -0.19
    ÑĥÑī
    -0.17
    ouser
    -0.16
    ê¼
    -0.14
    936
    -0.14
    claimer
    -0.14
    ÑĩаÑģно
    -0.14
    pcodes
    -0.14
    927
    -0.14
    emento
    -0.14
    POSITIVE LOGITS
     overnight
    0.26
     static
    0.23
    overn
    0.21
     rocket
    0.21
     Overnight
    0.20
     exclusive
    0.20
     isolated
    0.19
     linear
    0.19
    rocket
    0.18
     magic
    0.18
    Act Density 0.179%

    No Known Activations