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

    Neuronpedia

    INDEX
    Explanations

    topics related to social and political issues

    oai_token-act-pair · gpt-3.5-turbo

    expressions of dissatisfaction or complaints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estyles
    -0.61
    ãĤ´ãĥ³
    -0.58
    endum
    -0.57
     Timeline
    -0.56
    iece
    -0.56
     Canaver
    -0.55
    ãĥ©
    -0.55
    ãĤ»
    -0.53
    ished
    -0.53
    ubuntu
    -0.53
    POSITIVE LOGITS
    they
    1.19
     THEY
    1.16
    their
    1.15
    They
    1.14
     theirs
    1.12
     THEIR
    1.12
     they
    1.10
     They
    0.98
     themselves
    0.98
    Their
    0.94
    Act Density 1.317%

    No Known Activations