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

    Neuronpedia

    INDEX
    Explanations

    terms related to various forms of discrimination or anti-group sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iless
    -0.15
    elon
    -0.15
    ListOf
    -0.14
    antom
    -0.14
    egov
    -0.14
    ego
    -0.14
     Roose
    -0.14
    ohl
    -0.13
    ãĥ³ãĤ¸
    -0.13
    egen
    -0.13
    POSITIVE LOGITS
     sentiment
    0.35
     sentiments
    0.30
     Sent
    0.27
     measures
    0.23
    Sent
    0.23
     forces
    0.21
     stance
    0.21
     Measures
    0.20
    sent
    0.19
     activity
    0.19
    Act Density 0.040%

    No Known Activations