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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "down."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ">//
    -0.68
    ophon
    -0.60
     Geste
    -0.60
     referenties
    -0.59
    NameInMap
    -0.58
     Galer
    -0.58
    PhysRevD
    -0.57
    colage
    -0.56
    jgl
    -0.55
    frist
    -0.55
    POSITIVE LOGITS
     down
    1.18
    TagMode
    0.68
    Serde
    0.62
    ]</
    0.58
    glLoadIdentity
    0.57
    LookAnd
    0.55
    xture
    0.55
    Yup
    0.53
    اطر
    0.53
    InputBorder
    0.52
    Act Density 0.122%

    No Known Activations