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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts related to personal identity and self-discovery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Minds
    -0.15
    ungle
    -0.15
     Mans
    -0.14
    Ïĩε
    -0.14
    uc
    -0.14
    alist
    -0.14
    abl
    -0.14
    ablo
    -0.14
     Buffer
    -0.13
     close
    -0.13
    POSITIVE LOGITS
    identity
    0.21
    Identity
    0.20
    .Identity
    0.19
     Identity
    0.18
    _identity
    0.17
     identity
    0.17
    spender
    0.16
    åĦĢ
    0.15
    å²Ĺ
    0.15
    áº
    0.15
    Act Density 0.103%

    No Known Activations