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

    Neuronpedia

    INDEX
    Explanations

    words related to personal relationships and interactions

    oai_token-act-pair · gpt-3.5-turbo

    suffixes and endings of words, particularly those related to relationships and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imil
    -0.76
    ãĥ¼ãĥ«
    -0.72
    ENN
    -0.71
    bang
    -0.70
    soDeliveryDate
    -0.68
    Mos
    -0.68
    dinand
    -0.67
    Ãį
    -0.67
    infect
    -0.67
    VID
    -0.65
    POSITIVE LOGITS
    ttes
    0.77
    âĶĢ
    0.70
     thereof
    0.69
    hire
    0.68
    ously
    0.68
    yy
    0.67
    ially
    0.62
    dq
    0.62
     thereto
    0.60
    ktop
    0.60
    Act Density 0.620%

    No Known Activations