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

    Neuronpedia

    INDEX
    Explanations

    instances of direct quotes or speech in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vault
    -0.17
    uye
    -0.16
     Vault
    -0.15
    apas
    -0.15
    ÑĢаг
    -0.14
    cele
    -0.13
    PK
    -0.13
     Mean
    -0.13
     toilets
    -0.13
    IQ
    -0.13
    POSITIVE LOGITS
    eyh
    0.19
    -fw
    0.14
    zier
    0.14
    ober
    0.14
    erton
    0.14
    иÑĢÑĥ
    0.14
    linger
    0.14
    YST
    0.14
    SCII
    0.14
     IID
    0.14
    Act Density 0.061%

    No Known Activations