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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating adaptability and adjustment to new situations or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    memberOf
    -0.15
    olec
    -0.15
    Observable
    -0.14
     Rubin
    -0.14
    anas
    -0.14
    elper
    -0.14
     misunderstood
    -0.14
    asha
    -0.14
    aÄŁ
    -0.13
    oundingBox
    -0.13
    POSITIVE LOGITS
     used
    0.58
     Used
    0.53
     accustomed
    0.52
    Used
    0.52
    used
    0.50
     USED
    0.49
    -used
    0.46
    .used
    0.44
    _used
    0.42
    USED
    0.42
    Act Density 0.173%

    No Known Activations