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

    Neuronpedia

    INDEX
    Explanations

    references to criminal behavior and legal terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.85
     AssemblyVersion
    -0.78
    ,
    -0.74
     BoxDecoration
    -0.67
    ;
    -0.63
     —
    -0.60
    +#+
    -0.59
    TagHelpers
    -0.58
     ,
    -0.57
    ?
    -0.55
    POSITIVE LOGITS
     myſelf
    0.86
     itſelf
    0.81
     ſind
    0.76
     ſhould
    0.75
    ſelf
    0.74
     iſt
    0.74
     alſo
    0.73
     Baillargeon
    0.70
     Eſ
    0.70
     ſeveral
    0.70
    Act Density 0.187%

    No Known Activations