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

    Neuronpedia

    INDEX
    Explanations

    phrases related to controversy or significant reactions within the context of societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ihilation
    -0.16
    apult
    -0.14
     DISCLAIMER
    -0.14
     Fluid
    -0.13
    failure
    -0.13
    adiator
    -0.13
    laz
    -0.13
    pective
    -0.13
    otechn
    -0.12
     Empresa
    -0.12
    POSITIVE LOGITS
     comm
    0.39
     fur
    0.37
     stir
    0.36
     hull
    0.34
     hub
    0.31
     ker
    0.31
     fuss
    0.30
    fur
    0.30
     hue
    0.29
     buzz
    0.28
    Act Density 0.144%

    No Known Activations