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

    Neuronpedia

    INDEX
    Explanations

    terms related to illusions and deceptive perceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    illusion, delusion, hallucination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.46
    ⎧
    -0.44
    IBA
    -0.44
     rubrique
    -0.41
    mtable
    -0.41
    getR
    -0.41
     treba
    -0.40
    therly
    -0.40
     algemene
    -0.40
    INH
    -0.40
    POSITIVE LOGITS
     illusion
    1.91
     Illusion
    1.73
    illusion
    1.64
     illusions
    1.63
     ilusión
    1.20
     ilu
    1.06
     delusion
    1.06
     illusory
    1.03
     иллю
    0.91
     disillusion
    0.88
    Act Density 0.006%

    No Known Activations