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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific dates and numbers

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicative of problems or issues related to technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Merit
    -0.75
    ien
    -0.74
    ication
    -0.72
    nos
    -0.70
    ogi
    -0.70
    Facebook
    -0.69
    asso
    -0.69
    iss
    -0.69
    steamapps
    -0.68
     Winn
    -0.68
    POSITIVE LOGITS
    ãĥ¼ãĥĨãĤ£
    0.77
    bara
    0.76
    TER
    0.76
    dat
    0.75
     pixel
    0.74
    Dat
    0.71
     TER
    0.70
    ãĥĩãĤ£
    0.69
     ;;
    0.67
    ãĥĢ
    0.66
    Act Density 0.533%

    No Known Activations