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

    Neuronpedia

    INDEX
    Explanations

    negative statements or doubts about beliefs and expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.19
    itou
    -0.17
    ControlEvents
    -0.17
    ))?
    -0.16
    VERTISE
    -0.15
    DataURL
    -0.14
    actionDate
    -0.14
    holm
    -0.14
    âĢ¦"↵↵
    -0.14
    aÄĩ
    -0.14
    POSITIVE LOGITS
    rides
    0.17
     scenario
    0.15
    -the
    0.15
    ieval
    0.15
    /or
    0.15
     Dok
    0.14
     Kral
    0.14
    åĦ
    0.14
    -b
    0.14
     landlord
    0.14
    Act Density 0.111%

    No Known Activations