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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negative emotions or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uta
    -0.16
     Bulk
    -0.15
    ENSE
    -0.14
    º
    -0.14
    633
    -0.13
    ing
    -0.13
    _DICT
    -0.13
    chyb
    -0.13
    ULK
    -0.13
    лаÑĩ
    -0.13
    POSITIVE LOGITS
    Finance
    0.17
    /or
    0.15
    TEE
    0.15
    財
    0.15
     Finance
    0.15
     diseñador
    0.15
    UserCode
    0.15
    Ĥ¬
    0.15
    ека
    0.14
    ihanna
    0.14
    Act Density 0.046%

    No Known Activations