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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal cases and proceedings

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -1.04
     millenn
    -0.91
     disturb
    -0.84
    izoph
    -0.83
     challeng
    -0.83
     feasible
    -0.81
     activ
    -0.80
     setups
    -0.79
     undermin
    -0.79
     carbohyd
    -0.78
    POSITIVE LOGITS
     His
    1.55
     He
    1.48
     Others
    1.31
     Fellow
    1.25
     Former
    1.20
     Another
    1.17
     She
    1.17
     Previously
    1.15
     Other
    1.12
     Earlier
    1.09
    Act Density 0.337%

    No Known Activations