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

    Neuronpedia

    INDEX
    Explanations

    references to physical locations and spatial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jer
    -0.17
    errer
    -0.16
    .annot
    -0.15
    mue
    -0.14
    iaux
    -0.14
    еÑģп
    -0.14
    ÑĢÑĥÑģ
    -0.14
    tual
    -0.14
    APPER
    -0.14
    659
    -0.14
    POSITIVE LOGITS
     heads
    0.30
    -head
    0.26
     head
    0.25
     roof
    0.24
    heads
    0.24
    top
    0.24
     roofs
    0.23
    head
    0.23
     rooft
    0.22
    roof
    0.22
    Act Density 0.101%

    No Known Activations