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

    Neuronpedia

    INDEX
    Explanations

    phrases related to terms and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gros
    -0.18
    ellers
    -0.16
    att
    -0.16
    eller
    -0.16
     att
    -0.15
    igure
    -0.15
    mand
    -0.14
    .conf
    -0.14
     mand
    -0.14
    enc
    -0.13
    POSITIVE LOGITS
    inalg
    0.17
    setLayout
    0.16
    raj
    0.15
    conds
    0.15
    verity
    0.15
    OperationException
    0.15
     derp
    0.15
    inke
    0.15
    ascus
    0.15
    áºł
    0.14
    Act Density 0.003%

    No Known Activations