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

    Neuronpedia

    INDEX
    Explanations

    comparative statements emphasizing the degree of positivity or negativity

    oai_token-act-pair · gpt-3.5-turbo

    comparative evaluations and degrees of quality regarding various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arnaev
    -0.70
    hao
    -0.66
    ping
    -0.64
    rug
    -0.64
     brothers
    -0.64
     Romans
    -0.60
    azor
    -0.58
    enium
    -0.58
     Corm
    -0.58
    aternity
    -0.58
    POSITIVE LOGITS
    é¾įå
    0.83
    åħī
    0.79
     glance
    0.79
    FontSize
    0.75
    ç¥ŀ
    0.72
     BaseType
    0.70
    é¾įå¥ij士
    0.70
     è£ıè
    0.69
    ICA
    0.69
    ãĥīãĥ©ãĤ´ãĥ³
    0.69
    Act Density 0.035%

    No Known Activations