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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to software updates and management

    oai_token-act-pair · gpt-3.5-turbo

    terms related to technology and event management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾įå
    -0.84
    æ©
    -0.75
    âĹ¼
    -0.73
    ãģĦ
    -0.70
    çĶ°
    -0.69
    Ire
    -0.68
    æĢ
    -0.66
    ãģį
    -0.66
    acly
    -0.66
    bledon
    -0.64
    POSITIVE LOGITS
    naire
    0.67
    ↵↵
    0.62
     heats
    0.59
    ifies
    0.59
     welcomes
    0.59
    Joined
    0.59
    undrum
    0.58
    ↵
    0.57
     exploded
    0.57
    malink
    0.56
    Act Density 0.462%

    No Known Activations