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

    Neuronpedia

    INDEX
    Explanations

    references to walls and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     noires
    -0.64
    protoimpl
    -0.60
    lano
    -0.60
     chaud
    -0.59
     estekak
    -0.57
     doigts
    -0.57
    lijk
    -0.56
    alyptus
    -0.56
    AutoScale
    -0.56
    ology
    -0.56
    POSITIVE LOGITS
    PAPER
    0.64
     murals
    0.61
     Mur
    0.61
    Mur
    0.61
     WALL
    0.60
    papers
    0.58
    ThroughAttribute
    0.58
     mural
    0.57
     thickness
    0.55
    mounted
    0.55
    Act Density 0.154%

    No Known Activations