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

    Neuronpedia

    INDEX
    Explanations

    words related to the development of software functionalities

    oai_token-act-pair · gpt-3.5-turbo

    words related to invention or creation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oline
    -0.72
    balance
    -0.70
    cong
    -0.70
     Count
    -0.69
    ban
    -0.68
    Angelo
    -0.64
    occ
    -0.63
    Card
    -0.61
    rough
    -0.61
    cart
    -0.60
    POSITIVE LOGITS
    webkit
    0.85
     mathemat
    0.79
    rha
    0.77
    Ò
    0.77
    ©¶æ
    0.76
    cised
    0.74
     rg
    0.71
    Æ
    0.71
     obser
    0.70
    nesium
    0.67
    Act Density 0.000%

    No Known Activations