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

    Neuronpedia

    INDEX
    Explanations

    numerical values in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    numerical ratings and financial aspects related to items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enhagen
    -0.79
     appell
    -0.77
    apego
    -0.77
    gom
    -0.77
    lihood
    -0.75
    sov
    -0.72
    finger
    -0.70
    verb
    -0.69
    glers
    -0.67
    gars
    -0.67
    POSITIVE LOGITS
     {*
    0.83
     USPS
    0.77
     Comcast
    0.76
     Seller
    0.74
     Cancel
    0.73
     Requires
    0.73
    ©¶æ¥µ
    0.69
     Sears
    0.69
     Maze
    0.68
     Rewards
    0.68
    Act Density 0.039%

    No Known Activations