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

    Neuronpedia

    INDEX
    Explanations

    references to the humanities and social sciences as fields of study

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    4
    -0.15
    8
    -0.15
     Todo
    -0.14
    uš
    -0.13
    ÑĥÑĪ
    -0.13
    3
    -0.13
    bounding
    -0.13
    edn
    -0.13
     CM
    -0.13
     symb
    -0.13
    POSITIVE LOGITS
     sciences
    0.39
     Sciences
    0.34
     Exact
    0.29
     exact
    0.29
     natural
    0.28
    exact
    0.28
    Exact
    0.27
     humanities
    0.27
    STEM
    0.26
     STEM
    0.26
    Act Density 0.111%

    No Known Activations