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

    Neuronpedia

    INDEX
    Explanations

    phrases related to data collection and user privacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĢÑĥÑĪ
    -0.15
    rees
    -0.15
    lee
    -0.14
    packing
    -0.14
    elage
    -0.14
     Fleming
    -0.14
    .SIG
    -0.14
    _handles
    -0.13
    MBED
    -0.13
    elif
    -0.13
    POSITIVE LOGITS
     Snape
    0.17
     pup
    0.16
     inv
    0.16
     cast
    0.15
     incon
    0.15
     dr
    0.15
     tail
    0.14
     gre
    0.14
    aled
    0.14
     pseudo
    0.14
    Act Density 0.024%

    No Known Activations