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

    Neuronpedia

    INDEX
    Explanations

    references to legal actions and extradition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AST
    -0.15
    PPER
    -0.14
     assail
    -0.14
    esimal
    -0.13
    æ®
    -0.13
    llen
    -0.13
    _experiment
    -0.13
    ãĥ©ãĤ¯
    -0.13
    umm
    -0.13
    оÑī
    -0.13
    POSITIVE LOGITS
     extradition
    0.35
     extrad
    0.34
     fug
    0.32
     Wanted
    0.22
     warrant
    0.21
     warrants
    0.21
     appreh
    0.20
     wanted
    0.20
     arrest
    0.19
    wanted
    0.19
    Act Density 0.056%

    No Known Activations