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

    Neuronpedia

    INDEX
    Explanations

    types of biases or prejudices

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of biases and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vernment
    -0.81
    ãĥ©ãĥ³
    -0.74
    meet
    -0.57
    timer
    -0.56
    ãģĻ
    -0.55
    abba
    -0.55
    ãĤ¦ãĤ¹
    -0.55
    ergy
    -0.55
    ãĥ´
    -0.54
    clock
    -0.53
    POSITIVE LOGITS
     (-
    0.65
    alion
    0.65
    onica
    0.64
     (âĪĴ
    0.62
     (+
    0.60
    atible
    0.59
     Bog
    0.59
    IU
    0.59
    rique
    0.59
     Destination
    0.59
    Act Density 0.825%

    No Known Activations