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

    Neuronpedia

    INDEX
    Explanations

    words related to allegations and their context in legal or controversial situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    省市镇
    -0.49
    OfYear
    -0.44
    astify
    -0.44
     esternos
    -0.43
     Wartawan
    -0.43
     "..\..\
    -0.41
     "..\..\..\
    -0.40
    iastes
    -0.40
    scriber
    -0.39
     Signalez
    -0.39
    POSITIVE LOGITS
     expected
    1.38
     anticipated
    1.31
     alleged
    1.27
     supposed
    1.27
     suspected
    1.26
     presumed
    1.20
     preferred
    1.16
     desired
    1.13
     hoped
    1.11
     feared
    1.10
    Act Density 0.247%

    No Known Activations