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

    Neuronpedia

    INDEX
    Explanations

    phrases that contain the word "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vz
    -0.16
    928
    -0.15
    оваÑĢи
    -0.15
     rip
    -0.15
    ">//
    -0.14
    upa
    -0.14
    ulos
    -0.14
    sink
    -0.14
    oup
    -0.14
    /jpeg
    -0.13
    POSITIVE LOGITS
    oui
    0.18
    rogen
    0.15
    sten
    0.15
    dden
    0.15
    acket
    0.14
    ROTO
    0.14
    arin
    0.14
    oto
    0.14
    ile
    0.14
     Sah
    0.14
    Act Density 0.167%

    No Known Activations