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

    Neuronpedia

    INDEX
    Explanations

    negations and phrases that deny or contradict a preceding statement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enary
    -0.17
    aby
    -0.15
    oggles
    -0.14
    bao
    -0.14
    -addon
    -0.13
    een
    -0.13
    bac
    -0.13
    横
    -0.13
    <<
    -0.13
    qm
    -0.13
    POSITIVE LOGITS
    vice
    0.15
    ãĤĪ
    0.15
    ution
    0.15
     оно
    0.14
    isiyle
    0.14
    iable
    0.14
    å¤ķ
    0.14
    umlu
    0.14
    iline
    0.14
    afa
    0.14
    Act Density 0.017%

    No Known Activations