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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing frustration or criticism towards media and content quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iggins
    -0.16
    bes
    -0.15
    env
    -0.15
    idle
    -0.14
    ift
    -0.14
    iž
    -0.14
    ult
    -0.14
    gens
    -0.14
    ifting
    -0.14
    ewis
    -0.13
    POSITIVE LOGITS
     why
    0.16
    obi
    0.15
    ARSE
    0.15
    oir
    0.14
    ãĥ¼ãĥī
    0.14
    ÏĦζ
    0.14
    лÑĥÑĩ
    0.14
    usz
    0.14
    .future
    0.13
    دÙĨ
    0.13
    Act Density 0.113%

    No Known Activations