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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating praise or approval

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sports commentary or analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oshenko
    -0.75
     pit
    -0.72
     fermented
    -0.72
     deity
    -0.72
     metic
    -0.71
     pse
    -0.69
     grain
    -0.69
     tremend
    -0.67
    zel
    -0.67
     suspic
    -0.66
    POSITIVE LOGITS
     Unless
    1.02
     Ideally
    1.00
    Downloadha
    0.99
     Besides
    0.97
     However
    0.96
     Conversely
    0.96
     Lastly
    0.96
     Luckily
    0.96
     Otherwise
    0.96
     Alternatively
    0.95
    Act Density 1.382%

    No Known Activations