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

    Neuronpedia

    INDEX
    Explanations

    terms that denote the concept of "non" or negation in a variety of forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    841
    -0.18
    973
    -0.15
    untu
    -0.15
    ritis
    -0.15
    prov
    -0.15
    929
    -0.14
    chner
    -0.14
    amax
    -0.14
    970
    -0.14
    961
    -0.14
    POSITIVE LOGITS
     metro
    0.16
    ori
    0.15
     Metro
    0.14
    ogui
    0.14
    Occurred
    0.14
    еÑĤелÑĮ
    0.14
    icism
    0.14
    ammo
    0.14
    orks
    0.14
     defaultCenter
    0.14
    Act Density 0.018%

    No Known Activations