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

    Neuronpedia

    INDEX
    Explanations

    positive sentiments about experiences and services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    caler
    -0.15
    ANTED
    -0.14
    arro
    -0.14
    ilarity
    -0.14
     Else
    -0.14
    Otherwise
    -0.14
    apr
    -0.13
    otherwise
    -0.13
    iska
    -0.13
    UCE
    -0.13
    POSITIVE LOGITS
     lots
    0.20
     especially
    0.19
     such
    0.19
     wish
    0.18
     pity
    0.18
     Wish
    0.18
     unlike
    0.18
    wish
    0.17
     considering
    0.17
     obviously
    0.17
    Act Density 0.224%

    No Known Activations