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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sports and game scenarios

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     literature
    -0.82
     censored
    -0.81
     autonom
    -0.76
     oxy
    -0.75
     compan
    -0.74
     encl
    -0.74
     perspect
    -0.73
     undet
    -0.73
    orno
    -0.72
     ministerial
    -0.72
    POSITIVE LOGITS
     Granted
    1.21
     Additionally
    1.10
     Conversely
    1.08
     Obviously
    1.07
     Regardless
    1.06
     Unfortunately
    1.04
     Especially
    1.04
     Meanwhile
    1.04
     Passing
    1.04
     Considering
    1.02
    Act Density 0.376%

    No Known Activations