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

    Neuronpedia

    INDEX
    Explanations

    phrases that express negativity or extreme criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    441
    -0.17
    ized
    -0.16
    tron
    -0.15
    üçük
    -0.15
    hunt
    -0.15
    oria
    -0.15
    otate
    -0.15
    ÏģίοÏħ
    -0.14
    _maximum
    -0.14
    ect
    -0.14
    POSITIVE LOGITS
    ger
    0.22
    -case
    0.22
     Worse
    0.21
     worst
    0.20
     worse
    0.20
     Worst
    0.16
     ÑħÑĥд
    0.16
    ening
    0.15
    scenario
    0.15
     luck
    0.15
    Act Density 0.020%

    No Known Activations