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

    Neuronpedia

    INDEX
    Explanations

    references to the presence or discussion of cancer

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    tagext
    -0.68
     &___
    -0.67
     surla
    -0.65
    pasti
    -0.64
    NameInMap
    -0.63
    openzeppelin
    -0.63
    󠁢
    -0.63
    #+#
    -0.62
    躇
    -0.62
    AddTagHelper
    -0.61
    POSITIVE LOGITS
     Cancer
    0.99
    Cancer
    0.75
    psum
    0.74
     ammi
    0.72
     synt
    0.61
    punctuation
    0.59
    valu
    0.58
     deputies
    0.57
     semin
    0.57
    logout
    0.56
    Act Density 0.065%

    No Known Activations